From a624ae06756cb883c4a6b870f58e4bb3f39d9e45 Mon Sep 17 00:00:00 2001
From: Ines Montani <ines@ines.io>
Date: Wed, 22 Jul 2020 23:09:01 +0200
Subject: [PATCH] Remove POS, TAG and LEMMA from tokenizer exceptions

---
 spacy/lang/ar/tokenizer_exceptions.py         |   46 +-
 spacy/lang/bn/tokenizer_exceptions.py         |   26 +-
 spacy/lang/ca/tokenizer_exceptions.py         |   44 +-
 spacy/lang/da/tokenizer_exceptions.py         |  112 +-
 spacy/lang/de/tokenizer_exceptions.py         |  270 +-
 spacy/lang/el/tokenizer_exceptions.py         |  178 +-
 spacy/lang/en/tokenizer_exceptions.py         |  475 ++-
 spacy/lang/es/tokenizer_exceptions.py         |   36 +-
 spacy/lang/fa/tokenizer_exceptions.py         | 3494 ++++-------------
 spacy/lang/fi/tokenizer_exceptions.py         |  138 +-
 spacy/lang/fr/tokenizer_exceptions.py         |   92 +-
 spacy/lang/ga/tokenizer_exceptions.py         |  124 +-
 spacy/lang/id/tokenizer_exceptions.py         |   52 +-
 spacy/lang/it/tokenizer_exceptions.py         |    4 +-
 spacy/lang/lb/tokenizer_exceptions.py         |   28 +-
 spacy/lang/lij/tokenizer_exceptions.py        |   71 +-
 spacy/lang/nb/tokenizer_exceptions.py         |   24 +-
 spacy/lang/ru/tokenizer_exceptions.py         |   84 +-
 spacy/lang/sr/tokenizer_exceptions.py         |  130 +-
 spacy/lang/sv/tokenizer_exceptions.py         |   87 +-
 spacy/lang/th/tokenizer_exceptions.py         |  865 ++--
 spacy/lang/tl/tokenizer_exceptions.py         |   20 +-
 spacy/lang/tokenizer_exceptions.py            |   14 +-
 spacy/lang/tt/tokenizer_exceptions.py         |   49 +-
 spacy/lang/uk/tokenizer_exceptions.py         |   28 +-
 spacy/tests/lang/ar/test_exceptions.py        |    1 -
 spacy/tests/lang/ca/test_exception.py         |    2 -
 spacy/tests/lang/de/test_exceptions.py        |    1 -
 spacy/tests/lang/en/test_exceptions.py        |    2 -
 spacy/tests/lang/es/test_exception.py         |    2 -
 spacy/tests/lang/fr/test_exceptions.py        |   19 +-
 spacy/tests/lang/lb/test_exceptions.py        |    1 -
 spacy/tests/regression/test_issue1501-2000.py |    2 -
 spacy/tests/regression/test_issue2501-3000.py |    1 -
 34 files changed, 2173 insertions(+), 4349 deletions(-)

diff --git a/spacy/lang/ar/tokenizer_exceptions.py b/spacy/lang/ar/tokenizer_exceptions.py
index ce0f91ef7..7c385bef8 100644
--- a/spacy/lang/ar/tokenizer_exceptions.py
+++ b/spacy/lang/ar/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -8,41 +8,41 @@ _exc = {}
 
 # Time
 for exc_data in [
-    {LEMMA: "قبل الميلاد", ORTH: "ق.م"},
-    {LEMMA: "بعد الميلاد", ORTH: "ب. م"},
-    {LEMMA: "ميلادي", ORTH: ".م"},
-    {LEMMA: "هجري", ORTH: ".هـ"},
-    {LEMMA: "توفي", ORTH: ".ت"},
+    {NORM: "قبل الميلاد", ORTH: "ق.م"},
+    {NORM: "بعد الميلاد", ORTH: "ب. م"},
+    {NORM: "ميلادي", ORTH: ".م"},
+    {NORM: "هجري", ORTH: ".هـ"},
+    {NORM: "توفي", ORTH: ".ت"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
 # Scientific abv.
 for exc_data in [
-    {LEMMA: "صلى الله عليه وسلم", ORTH: "صلعم"},
-    {LEMMA: "الشارح", ORTH: "الشـ"},
-    {LEMMA: "الظاهر", ORTH: "الظـ"},
-    {LEMMA: "أيضًا", ORTH: "أيضـ"},
-    {LEMMA: "إلى آخره", ORTH: "إلخ"},
-    {LEMMA: "انتهى", ORTH: "اهـ"},
-    {LEMMA: "حدّثنا", ORTH: "ثنا"},
-    {LEMMA: "حدثني", ORTH: "ثنى"},
-    {LEMMA: "أنبأنا", ORTH: "أنا"},
-    {LEMMA: "أخبرنا", ORTH: "نا"},
-    {LEMMA: "مصدر سابق", ORTH: "م. س"},
-    {LEMMA: "مصدر نفسه", ORTH: "م. ن"},
+    {NORM: "صلى الله عليه وسلم", ORTH: "صلعم"},
+    {NORM: "الشارح", ORTH: "الشـ"},
+    {NORM: "الظاهر", ORTH: "الظـ"},
+    {NORM: "أيضًا", ORTH: "أيضـ"},
+    {NORM: "إلى آخره", ORTH: "إلخ"},
+    {NORM: "انتهى", ORTH: "اهـ"},
+    {NORM: "حدّثنا", ORTH: "ثنا"},
+    {NORM: "حدثني", ORTH: "ثنى"},
+    {NORM: "أنبأنا", ORTH: "أنا"},
+    {NORM: "أخبرنا", ORTH: "نا"},
+    {NORM: "مصدر سابق", ORTH: "م. س"},
+    {NORM: "مصدر نفسه", ORTH: "م. ن"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
 # Other abv.
 for exc_data in [
-    {LEMMA: "دكتور", ORTH: "د."},
-    {LEMMA: "أستاذ دكتور", ORTH: "أ.د"},
-    {LEMMA: "أستاذ", ORTH: "أ."},
-    {LEMMA: "بروفيسور", ORTH: "ب."},
+    {NORM: "دكتور", ORTH: "د."},
+    {NORM: "أستاذ دكتور", ORTH: "أ.د"},
+    {NORM: "أستاذ", ORTH: "أ."},
+    {NORM: "بروفيسور", ORTH: "ب."},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
-for exc_data in [{LEMMA: "تلفون", ORTH: "ت."}, {LEMMA: "صندوق بريد", ORTH: "ص.ب"}]:
+for exc_data in [{NORM: "تلفون", ORTH: "ت."}, {NORM: "صندوق بريد", ORTH: "ص.ب"}]:
     _exc[exc_data[ORTH]] = [exc_data]
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
diff --git a/spacy/lang/bn/tokenizer_exceptions.py b/spacy/lang/bn/tokenizer_exceptions.py
index d896b4914..e666522b8 100644
--- a/spacy/lang/bn/tokenizer_exceptions.py
+++ b/spacy/lang/bn/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -7,18 +7,18 @@ _exc = {}
 
 
 for exc_data in [
-    {ORTH: "ডঃ", LEMMA: "ডক্টর"},
-    {ORTH: "ডাঃ", LEMMA: "ডাক্তার"},
-    {ORTH: "ড.", LEMMA: "ডক্টর"},
-    {ORTH: "ডা.", LEMMA: "ডাক্তার"},
-    {ORTH: "মোঃ", LEMMA: "মোহাম্মদ"},
-    {ORTH: "মো.", LEMMA: "মোহাম্মদ"},
-    {ORTH: "সে.", LEMMA: "সেলসিয়াস"},
-    {ORTH: "কি.মি.", LEMMA: "কিলোমিটার"},
-    {ORTH: "কি.মি", LEMMA: "কিলোমিটার"},
-    {ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
-    {ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
-    {ORTH: "মি.লি.", LEMMA: "মিলিলিটার"},
+    {ORTH: "ডঃ", NORM: "ডক্টর"},
+    {ORTH: "ডাঃ", NORM: "ডাক্তার"},
+    {ORTH: "ড.", NORM: "ডক্টর"},
+    {ORTH: "ডা.", NORM: "ডাক্তার"},
+    {ORTH: "মোঃ", NORM: "মোহাম্মদ"},
+    {ORTH: "মো.", NORM: "মোহাম্মদ"},
+    {ORTH: "সে.", NORM: "সেলসিয়াস"},
+    {ORTH: "কি.মি.", NORM: "কিলোমিটার"},
+    {ORTH: "কি.মি", NORM: "কিলোমিটার"},
+    {ORTH: "সে.মি.", NORM: "সেন্টিমিটার"},
+    {ORTH: "সে.মি", NORM: "সেন্টিমিটার"},
+    {ORTH: "মি.লি.", NORM: "মিলিলিটার"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/ca/tokenizer_exceptions.py b/spacy/lang/ca/tokenizer_exceptions.py
index 6928de46b..b465e97ba 100644
--- a/spacy/lang/ca/tokenizer_exceptions.py
+++ b/spacy/lang/ca/tokenizer_exceptions.py
@@ -1,40 +1,40 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
 _exc = {}
 
 for exc_data in [
-    {ORTH: "aprox.", LEMMA: "aproximadament"},
-    {ORTH: "pàg.", LEMMA: "pàgina"},
-    {ORTH: "p.ex.", LEMMA: "per exemple"},
-    {ORTH: "gen.", LEMMA: "gener"},
-    {ORTH: "feb.", LEMMA: "febrer"},
-    {ORTH: "abr.", LEMMA: "abril"},
-    {ORTH: "jul.", LEMMA: "juliol"},
-    {ORTH: "set.", LEMMA: "setembre"},
-    {ORTH: "oct.", LEMMA: "octubre"},
-    {ORTH: "nov.", LEMMA: "novembre"},
-    {ORTH: "dec.", LEMMA: "desembre"},
-    {ORTH: "Dr.", LEMMA: "doctor"},
-    {ORTH: "Sr.", LEMMA: "senyor"},
-    {ORTH: "Sra.", LEMMA: "senyora"},
-    {ORTH: "Srta.", LEMMA: "senyoreta"},
-    {ORTH: "núm", LEMMA: "número"},
-    {ORTH: "St.", LEMMA: "sant"},
-    {ORTH: "Sta.", LEMMA: "santa"},
+    {ORTH: "aprox.", NORM: "aproximadament"},
+    {ORTH: "pàg.", NORM: "pàgina"},
+    {ORTH: "p.ex.", NORM: "per exemple"},
+    {ORTH: "gen.", NORM: "gener"},
+    {ORTH: "feb.", NORM: "febrer"},
+    {ORTH: "abr.", NORM: "abril"},
+    {ORTH: "jul.", NORM: "juliol"},
+    {ORTH: "set.", NORM: "setembre"},
+    {ORTH: "oct.", NORM: "octubre"},
+    {ORTH: "nov.", NORM: "novembre"},
+    {ORTH: "dec.", NORM: "desembre"},
+    {ORTH: "Dr.", NORM: "doctor"},
+    {ORTH: "Sr.", NORM: "senyor"},
+    {ORTH: "Sra.", NORM: "senyora"},
+    {ORTH: "Srta.", NORM: "senyoreta"},
+    {ORTH: "núm", NORM: "número"},
+    {ORTH: "St.", NORM: "sant"},
+    {ORTH: "Sta.", NORM: "santa"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
 # Times
-_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", LEMMA: "p.m."}]
+_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", NORM: "p.m."}]
 
 for h in range(1, 12 + 1):
     for period in ["a.m.", "am"]:
-        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, LEMMA: "a.m."}]
+        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, NORM: "a.m."}]
     for period in ["p.m.", "pm"]:
-        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, LEMMA: "p.m."}]
+        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, NORM: "p.m."}]
 
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
diff --git a/spacy/lang/da/tokenizer_exceptions.py b/spacy/lang/da/tokenizer_exceptions.py
index 826a6077b..ce25c546b 100644
--- a/spacy/lang/da/tokenizer_exceptions.py
+++ b/spacy/lang/da/tokenizer_exceptions.py
@@ -3,7 +3,7 @@ Tokenizer Exceptions.
 Source: https://forkortelse.dk/ and various others.
 """
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -13,44 +13,44 @@ _exc = {}
 # (for "torsdag") are left out because they are ambiguous. The same is the case
 # for abbreviations "jul." and "Jul." ("juli").
 for exc_data in [
-    {ORTH: "Kbh.", LEMMA: "København", NORM: "København"},
-    {ORTH: "jan.", LEMMA: "januar"},
-    {ORTH: "febr.", LEMMA: "februar"},
-    {ORTH: "feb.", LEMMA: "februar"},
-    {ORTH: "mar.", LEMMA: "marts"},
-    {ORTH: "apr.", LEMMA: "april"},
-    {ORTH: "jun.", LEMMA: "juni"},
-    {ORTH: "aug.", LEMMA: "august"},
-    {ORTH: "sept.", LEMMA: "september"},
-    {ORTH: "sep.", LEMMA: "september"},
-    {ORTH: "okt.", LEMMA: "oktober"},
-    {ORTH: "nov.", LEMMA: "november"},
-    {ORTH: "dec.", LEMMA: "december"},
-    {ORTH: "man.", LEMMA: "mandag"},
-    {ORTH: "tirs.", LEMMA: "tirsdag"},
-    {ORTH: "ons.", LEMMA: "onsdag"},
-    {ORTH: "tor.", LEMMA: "torsdag"},
-    {ORTH: "tors.", LEMMA: "torsdag"},
-    {ORTH: "fre.", LEMMA: "fredag"},
-    {ORTH: "lør.", LEMMA: "lørdag"},
-    {ORTH: "Jan.", LEMMA: "januar"},
-    {ORTH: "Febr.", LEMMA: "februar"},
-    {ORTH: "Feb.", LEMMA: "februar"},
-    {ORTH: "Mar.", LEMMA: "marts"},
-    {ORTH: "Apr.", LEMMA: "april"},
-    {ORTH: "Jun.", LEMMA: "juni"},
-    {ORTH: "Aug.", LEMMA: "august"},
-    {ORTH: "Sept.", LEMMA: "september"},
-    {ORTH: "Sep.", LEMMA: "september"},
-    {ORTH: "Okt.", LEMMA: "oktober"},
-    {ORTH: "Nov.", LEMMA: "november"},
-    {ORTH: "Dec.", LEMMA: "december"},
-    {ORTH: "Man.", LEMMA: "mandag"},
-    {ORTH: "Tirs.", LEMMA: "tirsdag"},
-    {ORTH: "Ons.", LEMMA: "onsdag"},
-    {ORTH: "Fre.", LEMMA: "fredag"},
-    {ORTH: "Lør.", LEMMA: "lørdag"},
-    {ORTH: "og/eller", LEMMA: "og/eller", NORM: "og/eller"},
+    {ORTH: "Kbh.", NORM: "København"},
+    {ORTH: "jan.", NORM: "januar"},
+    {ORTH: "febr.", NORM: "februar"},
+    {ORTH: "feb.", NORM: "februar"},
+    {ORTH: "mar.", NORM: "marts"},
+    {ORTH: "apr.", NORM: "april"},
+    {ORTH: "jun.", NORM: "juni"},
+    {ORTH: "aug.", NORM: "august"},
+    {ORTH: "sept.", NORM: "september"},
+    {ORTH: "sep.", NORM: "september"},
+    {ORTH: "okt.", NORM: "oktober"},
+    {ORTH: "nov.", NORM: "november"},
+    {ORTH: "dec.", NORM: "december"},
+    {ORTH: "man.", NORM: "mandag"},
+    {ORTH: "tirs.", NORM: "tirsdag"},
+    {ORTH: "ons.", NORM: "onsdag"},
+    {ORTH: "tor.", NORM: "torsdag"},
+    {ORTH: "tors.", NORM: "torsdag"},
+    {ORTH: "fre.", NORM: "fredag"},
+    {ORTH: "lør.", NORM: "lørdag"},
+    {ORTH: "Jan.", NORM: "januar"},
+    {ORTH: "Febr.", NORM: "februar"},
+    {ORTH: "Feb.", NORM: "februar"},
+    {ORTH: "Mar.", NORM: "marts"},
+    {ORTH: "Apr.", NORM: "april"},
+    {ORTH: "Jun.", NORM: "juni"},
+    {ORTH: "Aug.", NORM: "august"},
+    {ORTH: "Sept.", NORM: "september"},
+    {ORTH: "Sep.", NORM: "september"},
+    {ORTH: "Okt.", NORM: "oktober"},
+    {ORTH: "Nov.", NORM: "november"},
+    {ORTH: "Dec.", NORM: "december"},
+    {ORTH: "Man.", NORM: "mandag"},
+    {ORTH: "Tirs.", NORM: "tirsdag"},
+    {ORTH: "Ons.", NORM: "onsdag"},
+    {ORTH: "Fre.", NORM: "fredag"},
+    {ORTH: "Lør.", NORM: "lørdag"},
+    {ORTH: "og/eller", NORM: "og/eller"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
@@ -550,22 +550,22 @@ for orth in [
     _exc[capitalized] = [{ORTH: capitalized}]
 
 for exc_data in [
-    {ORTH: "s'gu", LEMMA: "s'gu", NORM: "s'gu"},
-    {ORTH: "S'gu", LEMMA: "s'gu", NORM: "s'gu"},
-    {ORTH: "sgu'", LEMMA: "s'gu", NORM: "s'gu"},
-    {ORTH: "Sgu'", LEMMA: "s'gu", NORM: "s'gu"},
-    {ORTH: "sku'", LEMMA: "skal", NORM: "skulle"},
-    {ORTH: "ku'", LEMMA: "kan", NORM: "kunne"},
-    {ORTH: "Ku'", LEMMA: "kan", NORM: "kunne"},
-    {ORTH: "ka'", LEMMA: "kan", NORM: "kan"},
-    {ORTH: "Ka'", LEMMA: "kan", NORM: "kan"},
-    {ORTH: "gi'", LEMMA: "give", NORM: "giv"},
-    {ORTH: "Gi'", LEMMA: "give", NORM: "giv"},
-    {ORTH: "li'", LEMMA: "lide", NORM: "lide"},
-    {ORTH: "ha'", LEMMA: "have", NORM: "have"},
-    {ORTH: "Ha'", LEMMA: "have", NORM: "have"},
-    {ORTH: "ik'", LEMMA: "ikke", NORM: "ikke"},
-    {ORTH: "Ik'", LEMMA: "ikke", NORM: "ikke"},
+    {ORTH: "s'gu", NORM: "s'gu"},
+    {ORTH: "S'gu", NORM: "s'gu"},
+    {ORTH: "sgu'", NORM: "s'gu"},
+    {ORTH: "Sgu'", NORM: "s'gu"},
+    {ORTH: "sku'", NORM: "skulle"},
+    {ORTH: "ku'", NORM: "kunne"},
+    {ORTH: "Ku'", NORM: "kunne"},
+    {ORTH: "ka'", NORM: "kan"},
+    {ORTH: "Ka'", NORM: "kan"},
+    {ORTH: "gi'", NORM: "giv"},
+    {ORTH: "Gi'", NORM: "giv"},
+    {ORTH: "li'", NORM: "lide"},
+    {ORTH: "ha'", NORM: "have"},
+    {ORTH: "Ha'", NORM: "have"},
+    {ORTH: "ik'", NORM: "ikke"},
+    {ORTH: "Ik'", NORM: "ikke"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
@@ -575,7 +575,7 @@ for h in range(1, 31 + 1):
     for period in ["."]:
         _exc[f"{h}{period}"] = [{ORTH: f"{h}."}]
 
-_custom_base_exc = {"i.": [{ORTH: "i", LEMMA: "i", NORM: "i"}, {ORTH: "."}]}
+_custom_base_exc = {"i.": [{ORTH: "i", NORM: "i"}, {ORTH: "."}]}
 _exc.update(_custom_base_exc)
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
diff --git a/spacy/lang/de/tokenizer_exceptions.py b/spacy/lang/de/tokenizer_exceptions.py
index d7860ace6..21d99cffe 100644
--- a/spacy/lang/de/tokenizer_exceptions.py
+++ b/spacy/lang/de/tokenizer_exceptions.py
@@ -1,159 +1,135 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, TAG, NORM, PRON_LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
 _exc = {
-    "auf'm": [{ORTH: "auf", LEMMA: "auf"}, {ORTH: "'m", LEMMA: "der", NORM: "dem"}],
-    "du's": [
-        {ORTH: "du", LEMMA: PRON_LEMMA, TAG: "PPER"},
-        {ORTH: "'s", LEMMA: PRON_LEMMA, TAG: "PPER", NORM: "es"},
-    ],
-    "er's": [
-        {ORTH: "er", LEMMA: PRON_LEMMA, TAG: "PPER"},
-        {ORTH: "'s", LEMMA: PRON_LEMMA, TAG: "PPER", NORM: "es"},
-    ],
-    "hinter'm": [
-        {ORTH: "hinter", LEMMA: "hinter"},
-        {ORTH: "'m", LEMMA: "der", NORM: "dem"},
-    ],
-    "ich's": [
-        {ORTH: "ich", LEMMA: PRON_LEMMA, TAG: "PPER"},
-        {ORTH: "'s", LEMMA: PRON_LEMMA, TAG: "PPER", NORM: "es"},
-    ],
-    "ihr's": [
-        {ORTH: "ihr", LEMMA: PRON_LEMMA, TAG: "PPER"},
-        {ORTH: "'s", LEMMA: PRON_LEMMA, TAG: "PPER", NORM: "es"},
-    ],
-    "sie's": [
-        {ORTH: "sie", LEMMA: PRON_LEMMA, TAG: "PPER"},
-        {ORTH: "'s", LEMMA: PRON_LEMMA, TAG: "PPER", NORM: "es"},
-    ],
-    "unter'm": [
-        {ORTH: "unter", LEMMA: "unter"},
-        {ORTH: "'m", LEMMA: "der", NORM: "dem"},
-    ],
-    "vor'm": [{ORTH: "vor", LEMMA: "vor"}, {ORTH: "'m", LEMMA: "der", NORM: "dem"}],
-    "wir's": [
-        {ORTH: "wir", LEMMA: PRON_LEMMA, TAG: "PPER"},
-        {ORTH: "'s", LEMMA: PRON_LEMMA, TAG: "PPER", NORM: "es"},
-    ],
-    "über'm": [{ORTH: "über", LEMMA: "über"}, {ORTH: "'m", LEMMA: "der", NORM: "dem"}],
+    "auf'm": [{ORTH: "auf"}, {ORTH: "'m", NORM: "dem"}],
+    "du's": [{ORTH: "du"}, {ORTH: "'s", NORM: "es"}],
+    "er's": [{ORTH: "er"}, {ORTH: "'s", NORM: "es"}],
+    "hinter'm": [{ORTH: "hinter"}, {ORTH: "'m", NORM: "dem"}],
+    "ich's": [{ORTH: "ich"}, {ORTH: "'s", NORM: "es"}],
+    "ihr's": [{ORTH: "ihr"}, {ORTH: "'s", NORM: "es"}],
+    "sie's": [{ORTH: "sie"}, {ORTH: "'s", NORM: "es"}],
+    "unter'm": [{ORTH: "unter"}, {ORTH: "'m", NORM: "dem"}],
+    "vor'm": [{ORTH: "vor"}, {ORTH: "'m", NORM: "dem"}],
+    "wir's": [{ORTH: "wir"}, {ORTH: "'s", NORM: "es"}],
+    "über'm": [{ORTH: "über"}, {ORTH: "'m", NORM: "dem"}],
 }
 
 
 for exc_data in [
-    {ORTH: "'S", LEMMA: PRON_LEMMA, NORM: "'s", TAG: "PPER"},
-    {ORTH: "'s", LEMMA: PRON_LEMMA, NORM: "'s", TAG: "PPER"},
-    {ORTH: "S'", LEMMA: PRON_LEMMA, NORM: "'s", TAG: "PPER"},
-    {ORTH: "s'", LEMMA: PRON_LEMMA, NORM: "'s", TAG: "PPER"},
-    {ORTH: "'n", LEMMA: "ein", NORM: "ein"},
-    {ORTH: "'ne", LEMMA: "eine", NORM: "eine"},
-    {ORTH: "'nen", LEMMA: "ein", NORM: "einen"},
-    {ORTH: "'nem", LEMMA: "ein", NORM: "einem"},
-    {ORTH: "Abb.", LEMMA: "Abbildung", NORM: "Abbildung"},
-    {ORTH: "Abk.", LEMMA: "Abkürzung", NORM: "Abkürzung"},
-    {ORTH: "Abt.", LEMMA: "Abteilung", NORM: "Abteilung"},
-    {ORTH: "Apr.", LEMMA: "April", NORM: "April"},
-    {ORTH: "Aug.", LEMMA: "August", NORM: "August"},
-    {ORTH: "Bd.", LEMMA: "Band", NORM: "Band"},
-    {ORTH: "Betr.", LEMMA: "Betreff", NORM: "Betreff"},
-    {ORTH: "Bf.", LEMMA: "Bahnhof", NORM: "Bahnhof"},
-    {ORTH: "Bhf.", LEMMA: "Bahnhof", NORM: "Bahnhof"},
-    {ORTH: "Bsp.", LEMMA: "Beispiel", NORM: "Beispiel"},
-    {ORTH: "Dez.", LEMMA: "Dezember", NORM: "Dezember"},
-    {ORTH: "Di.", LEMMA: "Dienstag", NORM: "Dienstag"},
-    {ORTH: "Do.", LEMMA: "Donnerstag", NORM: "Donnerstag"},
-    {ORTH: "Fa.", LEMMA: "Firma", NORM: "Firma"},
-    {ORTH: "Fam.", LEMMA: "Familie", NORM: "Familie"},
-    {ORTH: "Feb.", LEMMA: "Februar", NORM: "Februar"},
-    {ORTH: "Fr.", LEMMA: "Frau", NORM: "Frau"},
-    {ORTH: "Frl.", LEMMA: "Fräulein", NORM: "Fräulein"},
-    {ORTH: "Hbf.", LEMMA: "Hauptbahnhof", NORM: "Hauptbahnhof"},
-    {ORTH: "Hr.", LEMMA: "Herr", NORM: "Herr"},
-    {ORTH: "Hrn.", LEMMA: "Herr", NORM: "Herrn"},
-    {ORTH: "Jan.", LEMMA: "Januar", NORM: "Januar"},
-    {ORTH: "Jh.", LEMMA: "Jahrhundert", NORM: "Jahrhundert"},
-    {ORTH: "Jhd.", LEMMA: "Jahrhundert", NORM: "Jahrhundert"},
-    {ORTH: "Jul.", LEMMA: "Juli", NORM: "Juli"},
-    {ORTH: "Jun.", LEMMA: "Juni", NORM: "Juni"},
-    {ORTH: "Mi.", LEMMA: "Mittwoch", NORM: "Mittwoch"},
-    {ORTH: "Mio.", LEMMA: "Million", NORM: "Million"},
-    {ORTH: "Mo.", LEMMA: "Montag", NORM: "Montag"},
-    {ORTH: "Mrd.", LEMMA: "Milliarde", NORM: "Milliarde"},
-    {ORTH: "Mrz.", LEMMA: "März", NORM: "März"},
-    {ORTH: "MwSt.", LEMMA: "Mehrwertsteuer", NORM: "Mehrwertsteuer"},
-    {ORTH: "Mär.", LEMMA: "März", NORM: "März"},
-    {ORTH: "Nov.", LEMMA: "November", NORM: "November"},
-    {ORTH: "Nr.", LEMMA: "Nummer", NORM: "Nummer"},
-    {ORTH: "Okt.", LEMMA: "Oktober", NORM: "Oktober"},
-    {ORTH: "Orig.", LEMMA: "Original", NORM: "Original"},
-    {ORTH: "Pkt.", LEMMA: "Punkt", NORM: "Punkt"},
-    {ORTH: "Prof.", LEMMA: "Professor", NORM: "Professor"},
-    {ORTH: "Red.", LEMMA: "Redaktion", NORM: "Redaktion"},
-    {ORTH: "Sa.", LEMMA: "Samstag", NORM: "Samstag"},
-    {ORTH: "Sep.", LEMMA: "September", NORM: "September"},
-    {ORTH: "Sept.", LEMMA: "September", NORM: "September"},
-    {ORTH: "So.", LEMMA: "Sonntag", NORM: "Sonntag"},
-    {ORTH: "Std.", LEMMA: "Stunde", NORM: "Stunde"},
-    {ORTH: "Str.", LEMMA: "Straße", NORM: "Straße"},
-    {ORTH: "Tel.", LEMMA: "Telefon", NORM: "Telefon"},
-    {ORTH: "Tsd.", LEMMA: "Tausend", NORM: "Tausend"},
-    {ORTH: "Univ.", LEMMA: "Universität", NORM: "Universität"},
-    {ORTH: "abzgl.", LEMMA: "abzüglich", NORM: "abzüglich"},
-    {ORTH: "allg.", LEMMA: "allgemein", NORM: "allgemein"},
-    {ORTH: "bspw.", LEMMA: "beispielsweise", NORM: "beispielsweise"},
-    {ORTH: "bzgl.", LEMMA: "bezüglich", NORM: "bezüglich"},
-    {ORTH: "bzw.", LEMMA: "beziehungsweise", NORM: "beziehungsweise"},
-    {ORTH: "d.h.", LEMMA: "das heißt"},
-    {ORTH: "dgl.", LEMMA: "dergleichen", NORM: "dergleichen"},
-    {ORTH: "ebd.", LEMMA: "ebenda", NORM: "ebenda"},
-    {ORTH: "eigtl.", LEMMA: "eigentlich", NORM: "eigentlich"},
-    {ORTH: "engl.", LEMMA: "englisch", NORM: "englisch"},
-    {ORTH: "evtl.", LEMMA: "eventuell", NORM: "eventuell"},
-    {ORTH: "frz.", LEMMA: "französisch", NORM: "französisch"},
-    {ORTH: "gegr.", LEMMA: "gegründet", NORM: "gegründet"},
-    {ORTH: "ggf.", LEMMA: "gegebenenfalls", NORM: "gegebenenfalls"},
-    {ORTH: "ggfs.", LEMMA: "gegebenenfalls", NORM: "gegebenenfalls"},
-    {ORTH: "ggü.", LEMMA: "gegenüber", NORM: "gegenüber"},
-    {ORTH: "i.O.", LEMMA: "in Ordnung"},
-    {ORTH: "i.d.R.", LEMMA: "in der Regel"},
-    {ORTH: "incl.", LEMMA: "inklusive", NORM: "inklusive"},
-    {ORTH: "inkl.", LEMMA: "inklusive", NORM: "inklusive"},
-    {ORTH: "insb.", LEMMA: "insbesondere", NORM: "insbesondere"},
-    {ORTH: "kath.", LEMMA: "katholisch", NORM: "katholisch"},
-    {ORTH: "lt.", LEMMA: "laut", NORM: "laut"},
-    {ORTH: "max.", LEMMA: "maximal", NORM: "maximal"},
-    {ORTH: "min.", LEMMA: "minimal", NORM: "minimal"},
-    {ORTH: "mind.", LEMMA: "mindestens", NORM: "mindestens"},
-    {ORTH: "mtl.", LEMMA: "monatlich", NORM: "monatlich"},
-    {ORTH: "n.Chr.", LEMMA: "nach Christus"},
-    {ORTH: "orig.", LEMMA: "original", NORM: "original"},
-    {ORTH: "röm.", LEMMA: "römisch", NORM: "römisch"},
-    {ORTH: "s.o.", LEMMA: "siehe oben"},
-    {ORTH: "sog.", LEMMA: "so genannt"},
-    {ORTH: "stellv.", LEMMA: "stellvertretend"},
-    {ORTH: "tägl.", LEMMA: "täglich", NORM: "täglich"},
-    {ORTH: "u.U.", LEMMA: "unter Umständen"},
-    {ORTH: "u.s.w.", LEMMA: "und so weiter"},
-    {ORTH: "u.v.m.", LEMMA: "und vieles mehr"},
-    {ORTH: "usf.", LEMMA: "und so fort"},
-    {ORTH: "usw.", LEMMA: "und so weiter"},
-    {ORTH: "uvm.", LEMMA: "und vieles mehr"},
-    {ORTH: "v.Chr.", LEMMA: "vor Christus"},
-    {ORTH: "v.a.", LEMMA: "vor allem"},
-    {ORTH: "v.l.n.r.", LEMMA: "von links nach rechts"},
-    {ORTH: "vgl.", LEMMA: "vergleiche", NORM: "vergleiche"},
-    {ORTH: "vllt.", LEMMA: "vielleicht", NORM: "vielleicht"},
-    {ORTH: "vlt.", LEMMA: "vielleicht", NORM: "vielleicht"},
-    {ORTH: "z.B.", LEMMA: "zum Beispiel"},
-    {ORTH: "z.Bsp.", LEMMA: "zum Beispiel"},
-    {ORTH: "z.T.", LEMMA: "zum Teil"},
-    {ORTH: "z.Z.", LEMMA: "zur Zeit"},
-    {ORTH: "z.Zt.", LEMMA: "zur Zeit"},
-    {ORTH: "z.b.", LEMMA: "zum Beispiel"},
-    {ORTH: "zzgl.", LEMMA: "zuzüglich"},
-    {ORTH: "österr.", LEMMA: "österreichisch", NORM: "österreichisch"},
+    {ORTH: "'S", NORM: "'s"},
+    {ORTH: "'s", NORM: "'s"},
+    {ORTH: "S'", NORM: "'s"},
+    {ORTH: "s'", NORM: "'s"},
+    {ORTH: "'n", NORM: "ein"},
+    {ORTH: "'ne", NORM: "eine"},
+    {ORTH: "'nen", NORM: "einen"},
+    {ORTH: "'nem", NORM: "einem"},
+    {ORTH: "Abb.", NORM: "Abbildung"},
+    {ORTH: "Abk.", NORM: "Abkürzung"},
+    {ORTH: "Abt.", NORM: "Abteilung"},
+    {ORTH: "Apr.", NORM: "April"},
+    {ORTH: "Aug.", NORM: "August"},
+    {ORTH: "Bd.", NORM: "Band"},
+    {ORTH: "Betr.", NORM: "Betreff"},
+    {ORTH: "Bf.", NORM: "Bahnhof"},
+    {ORTH: "Bhf.", NORM: "Bahnhof"},
+    {ORTH: "Bsp.", NORM: "Beispiel"},
+    {ORTH: "Dez.", NORM: "Dezember"},
+    {ORTH: "Di.", NORM: "Dienstag"},
+    {ORTH: "Do.", NORM: "Donnerstag"},
+    {ORTH: "Fa.", NORM: "Firma"},
+    {ORTH: "Fam.", NORM: "Familie"},
+    {ORTH: "Feb.", NORM: "Februar"},
+    {ORTH: "Fr.", NORM: "Frau"},
+    {ORTH: "Frl.", NORM: "Fräulein"},
+    {ORTH: "Hbf.", NORM: "Hauptbahnhof"},
+    {ORTH: "Hr.", NORM: "Herr"},
+    {ORTH: "Hrn.", NORM: "Herrn"},
+    {ORTH: "Jan.", NORM: "Januar"},
+    {ORTH: "Jh.", NORM: "Jahrhundert"},
+    {ORTH: "Jhd.", NORM: "Jahrhundert"},
+    {ORTH: "Jul.", NORM: "Juli"},
+    {ORTH: "Jun.", NORM: "Juni"},
+    {ORTH: "Mi.", NORM: "Mittwoch"},
+    {ORTH: "Mio.", NORM: "Million"},
+    {ORTH: "Mo.", NORM: "Montag"},
+    {ORTH: "Mrd.", NORM: "Milliarde"},
+    {ORTH: "Mrz.", NORM: "März"},
+    {ORTH: "MwSt.", NORM: "Mehrwertsteuer"},
+    {ORTH: "Mär.", NORM: "März"},
+    {ORTH: "Nov.", NORM: "November"},
+    {ORTH: "Nr.", NORM: "Nummer"},
+    {ORTH: "Okt.", NORM: "Oktober"},
+    {ORTH: "Orig.", NORM: "Original"},
+    {ORTH: "Pkt.", NORM: "Punkt"},
+    {ORTH: "Prof.", NORM: "Professor"},
+    {ORTH: "Red.", NORM: "Redaktion"},
+    {ORTH: "Sa.", NORM: "Samstag"},
+    {ORTH: "Sep.", NORM: "September"},
+    {ORTH: "Sept.", NORM: "September"},
+    {ORTH: "So.", NORM: "Sonntag"},
+    {ORTH: "Std.", NORM: "Stunde"},
+    {ORTH: "Str.", NORM: "Straße"},
+    {ORTH: "Tel.", NORM: "Telefon"},
+    {ORTH: "Tsd.", NORM: "Tausend"},
+    {ORTH: "Univ.", NORM: "Universität"},
+    {ORTH: "abzgl.", NORM: "abzüglich"},
+    {ORTH: "allg.", NORM: "allgemein"},
+    {ORTH: "bspw.", NORM: "beispielsweise"},
+    {ORTH: "bzgl.", NORM: "bezüglich"},
+    {ORTH: "bzw.", NORM: "beziehungsweise"},
+    {ORTH: "d.h."},
+    {ORTH: "dgl.", NORM: "dergleichen"},
+    {ORTH: "ebd.", NORM: "ebenda"},
+    {ORTH: "eigtl.", NORM: "eigentlich"},
+    {ORTH: "engl.", NORM: "englisch"},
+    {ORTH: "evtl.", NORM: "eventuell"},
+    {ORTH: "frz.", NORM: "französisch"},
+    {ORTH: "gegr.", NORM: "gegründet"},
+    {ORTH: "ggf.", NORM: "gegebenenfalls"},
+    {ORTH: "ggfs.", NORM: "gegebenenfalls"},
+    {ORTH: "ggü.", NORM: "gegenüber"},
+    {ORTH: "i.O."},
+    {ORTH: "i.d.R."},
+    {ORTH: "incl.", NORM: "inklusive"},
+    {ORTH: "inkl.", NORM: "inklusive"},
+    {ORTH: "insb.", NORM: "insbesondere"},
+    {ORTH: "kath.", NORM: "katholisch"},
+    {ORTH: "lt.", NORM: "laut"},
+    {ORTH: "max.", NORM: "maximal"},
+    {ORTH: "min.", NORM: "minimal"},
+    {ORTH: "mind.", NORM: "mindestens"},
+    {ORTH: "mtl.", NORM: "monatlich"},
+    {ORTH: "n.Chr."},
+    {ORTH: "orig.", NORM: "original"},
+    {ORTH: "röm.", NORM: "römisch"},
+    {ORTH: "s.o."},
+    {ORTH: "sog."},
+    {ORTH: "stellv."},
+    {ORTH: "tägl.", NORM: "täglich"},
+    {ORTH: "u.U."},
+    {ORTH: "u.s.w."},
+    {ORTH: "u.v.m."},
+    {ORTH: "usf."},
+    {ORTH: "usw."},
+    {ORTH: "uvm."},
+    {ORTH: "v.Chr."},
+    {ORTH: "v.a."},
+    {ORTH: "v.l.n.r."},
+    {ORTH: "vgl.", NORM: "vergleiche"},
+    {ORTH: "vllt.", NORM: "vielleicht"},
+    {ORTH: "vlt.", NORM: "vielleicht"},
+    {ORTH: "z.B."},
+    {ORTH: "z.Bsp."},
+    {ORTH: "z.T."},
+    {ORTH: "z.Z."},
+    {ORTH: "z.Zt."},
+    {ORTH: "z.b."},
+    {ORTH: "zzgl."},
+    {ORTH: "österr.", NORM: "österreichisch"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/el/tokenizer_exceptions.py b/spacy/lang/el/tokenizer_exceptions.py
index f9810828b..0a36d5d2b 100644
--- a/spacy/lang/el/tokenizer_exceptions.py
+++ b/spacy/lang/el/tokenizer_exceptions.py
@@ -1,130 +1,128 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 _exc = {}
 
 for token in ["Απ'", "ΑΠ'", "αφ'", "Αφ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "από", NORM: "από"}]
+    _exc[token] = [{ORTH: token, NORM: "από"}]
 
 for token in ["Αλλ'", "αλλ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "αλλά", NORM: "αλλά"}]
+    _exc[token] = [{ORTH: token, NORM: "αλλά"}]
 
 for token in ["παρ'", "Παρ'", "ΠΑΡ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "παρά", NORM: "παρά"}]
+    _exc[token] = [{ORTH: token, NORM: "παρά"}]
 
 for token in ["καθ'", "Καθ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "κάθε", NORM: "κάθε"}]
+    _exc[token] = [{ORTH: token, NORM: "κάθε"}]
 
 for token in ["κατ'", "Κατ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "κατά", NORM: "κατά"}]
+    _exc[token] = [{ORTH: token, NORM: "κατά"}]
 
 for token in ["'ΣΟΥΝ", "'ναι", "'ταν", "'τανε", "'μαστε", "'μουνα", "'μουν"]:
-    _exc[token] = [{ORTH: token, LEMMA: "είμαι", NORM: "είμαι"}]
+    _exc[token] = [{ORTH: token, NORM: "είμαι"}]
 
 for token in ["Επ'", "επ'", "εφ'", "Εφ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "επί", NORM: "επί"}]
+    _exc[token] = [{ORTH: token, NORM: "επί"}]
 
 for token in ["Δι'", "δι'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "δια", NORM: "δια"}]
+    _exc[token] = [{ORTH: token, NORM: "δια"}]
 
 for token in ["'χουν", "'χουμε", "'χαμε", "'χα", "'χε", "'χεις", "'χει"]:
-    _exc[token] = [{ORTH: token, LEMMA: "έχω", NORM: "έχω"}]
+    _exc[token] = [{ORTH: token, NORM: "έχω"}]
 
 for token in ["υπ'", "Υπ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "υπό", NORM: "υπό"}]
+    _exc[token] = [{ORTH: token, NORM: "υπό"}]
 
 for token in ["Μετ'", "ΜΕΤ'", "'μετ"]:
-    _exc[token] = [{ORTH: token, LEMMA: "μετά", NORM: "μετά"}]
+    _exc[token] = [{ORTH: token, NORM: "μετά"}]
 
 for token in ["Μ'", "μ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "με", NORM: "με"}]
+    _exc[token] = [{ORTH: token, NORM: "με"}]
 
 for token in ["Γι'", "ΓΙ'", "γι'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "για", NORM: "για"}]
+    _exc[token] = [{ORTH: token, NORM: "για"}]
 
 for token in ["Σ'", "σ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "σε", NORM: "σε"}]
+    _exc[token] = [{ORTH: token, NORM: "σε"}]
 
 for token in ["Θ'", "θ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "θα", NORM: "θα"}]
+    _exc[token] = [{ORTH: token, NORM: "θα"}]
 
 for token in ["Ν'", "ν'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "να", NORM: "να"}]
+    _exc[token] = [{ORTH: token, NORM: "να"}]
 
 for token in ["Τ'", "τ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "να", NORM: "να"}]
+    _exc[token] = [{ORTH: token, NORM: "να"}]
 
 for token in ["'γω", "'σένα", "'μεις"]:
-    _exc[token] = [{ORTH: token, LEMMA: "εγώ", NORM: "εγώ"}]
+    _exc[token] = [{ORTH: token, NORM: "εγώ"}]
 
 for token in ["Τ'", "τ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "το", NORM: "το"}]
+    _exc[token] = [{ORTH: token, NORM: "το"}]
 
 for token in ["Φέρ'", "Φερ'", "φέρ'", "φερ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "φέρνω", NORM: "φέρνω"}]
+    _exc[token] = [{ORTH: token, NORM: "φέρνω"}]
 
 for token in ["'ρθούνε", "'ρθουν", "'ρθει", "'ρθεί", "'ρθε", "'ρχεται"]:
-    _exc[token] = [{ORTH: token, LEMMA: "έρχομαι", NORM: "έρχομαι"}]
+    _exc[token] = [{ORTH: token, NORM: "έρχομαι"}]
 
 for token in ["'πανε", "'λεγε", "'λεγαν", "'πε", "'λεγα"]:
-    _exc[token] = [{ORTH: token, LEMMA: "λέγω", NORM: "λέγω"}]
+    _exc[token] = [{ORTH: token, NORM: "λέγω"}]
 
 for token in ["Πάρ'", "πάρ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "παίρνω", NORM: "παίρνω"}]
+    _exc[token] = [{ORTH: token, NORM: "παίρνω"}]
 
 for token in ["μέσ'", "Μέσ'", "μεσ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "μέσα", NORM: "μέσα"}]
+    _exc[token] = [{ORTH: token, NORM: "μέσα"}]
 
 for token in ["Δέσ'", "Δεσ'", "δεσ'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "δένω", NORM: "δένω"}]
+    _exc[token] = [{ORTH: token, NORM: "δένω"}]
 
 for token in ["'κανε", "Κάν'"]:
-    _exc[token] = [{ORTH: token, LEMMA: "κάνω", NORM: "κάνω"}]
+    _exc[token] = [{ORTH: token, NORM: "κάνω"}]
 
 _other_exc = {
-    "κι": [{ORTH: "κι", LEMMA: "και", NORM: "και"}],
-    "Παίξ'": [{ORTH: "Παίξ'", LEMMA: "παίζω", NORM: "παίζω"}],
-    "Αντ'": [{ORTH: "Αντ'", LEMMA: "αντί", NORM: "αντί"}],
-    "ολ'": [{ORTH: "ολ'", LEMMA: "όλος", NORM: "όλος"}],
-    "ύστερ'": [{ORTH: "ύστερ'", LEMMA: "ύστερα", NORM: "ύστερα"}],
-    "'πρεπε": [{ORTH: "'πρεπε", LEMMA: "πρέπει", NORM: "πρέπει"}],
-    "Δύσκολ'": [{ORTH: "Δύσκολ'", LEMMA: "δύσκολος", NORM: "δύσκολος"}],
-    "'θελα": [{ORTH: "'θελα", LEMMA: "θέλω", NORM: "θέλω"}],
-    "'γραφα": [{ORTH: "'γραφα", LEMMA: "γράφω", NORM: "γράφω"}],
-    "'παιρνα": [{ORTH: "'παιρνα", LEMMA: "παίρνω", NORM: "παίρνω"}],
-    "'δειξε": [{ORTH: "'δειξε", LEMMA: "δείχνω", NORM: "δείχνω"}],
-    "όμουρφ'": [{ORTH: "όμουρφ'", LEMMA: "όμορφος", NORM: "όμορφος"}],
-    "κ'τσή": [{ORTH: "κ'τσή", LEMMA: "κουτσός", NORM: "κουτσός"}],
-    "μηδ'": [{ORTH: "μηδ'", LEMMA: "μήδε", NORM: "μήδε"}],
-    "'ξομολογήθηκε": [
-        {ORTH: "'ξομολογήθηκε", LEMMA: "εξομολογούμαι", NORM: "εξομολογούμαι"}
-    ],
-    "'μας": [{ORTH: "'μας", LEMMA: "εμάς", NORM: "εμάς"}],
-    "'ξερες": [{ORTH: "'ξερες", LEMMA: "ξέρω", NORM: "ξέρω"}],
-    "έφθασ'": [{ORTH: "έφθασ'", LEMMA: "φθάνω", NORM: "φθάνω"}],
-    "εξ'": [{ORTH: "εξ'", LEMMA: "εκ", NORM: "εκ"}],
-    "δώσ'": [{ORTH: "δώσ'", LEMMA: "δίνω", NORM: "δίνω"}],
-    "τίποτ'": [{ORTH: "τίποτ'", LEMMA: "τίποτα", NORM: "τίποτα"}],
-    "Λήξ'": [{ORTH: "Λήξ'", LEMMA: "λήγω", NORM: "λήγω"}],
-    "άσ'": [{ORTH: "άσ'", LEMMA: "αφήνω", NORM: "αφήνω"}],
-    "Στ'": [{ORTH: "Στ'", LEMMA: "στο", NORM: "στο"}],
-    "Δωσ'": [{ORTH: "Δωσ'", LEMMA: "δίνω", NORM: "δίνω"}],
-    "Βάψ'": [{ORTH: "Βάψ'", LEMMA: "βάφω", NORM: "βάφω"}],
-    "Αλλ'": [{ORTH: "Αλλ'", LEMMA: "αλλά", NORM: "αλλά"}],
-    "Αμ'": [{ORTH: "Αμ'", LEMMA: "άμα", NORM: "άμα"}],
-    "Αγόρασ'": [{ORTH: "Αγόρασ'", LEMMA: "αγοράζω", NORM: "αγοράζω"}],
-    "'φύγε": [{ORTH: "'φύγε", LEMMA: "φεύγω", NORM: "φεύγω"}],
-    "'φερε": [{ORTH: "'φερε", LEMMA: "φέρνω", NORM: "φέρνω"}],
-    "'φαγε": [{ORTH: "'φαγε", LEMMA: "τρώω", NORM: "τρώω"}],
-    "'σπαγαν": [{ORTH: "'σπαγαν", LEMMA: "σπάω", NORM: "σπάω"}],
-    "'σκασε": [{ORTH: "'σκασε", LEMMA: "σκάω", NORM: "σκάω"}],
-    "'σβηνε": [{ORTH: "'σβηνε", LEMMA: "σβήνω", NORM: "σβήνω"}],
-    "'ριξε": [{ORTH: "'ριξε", LEMMA: "ρίχνω", NORM: "ρίχνω"}],
-    "'κλεβε": [{ORTH: "'κλεβε", LEMMA: "κλέβω", NORM: "κλέβω"}],
-    "'κει": [{ORTH: "'κει", LEMMA: "εκεί", NORM: "εκεί"}],
-    "'βλεπε": [{ORTH: "'βλεπε", LEMMA: "βλέπω", NORM: "βλέπω"}],
-    "'βγαινε": [{ORTH: "'βγαινε", LEMMA: "βγαίνω", NORM: "βγαίνω"}],
+    "κι": [{ORTH: "κι", NORM: "και"}],
+    "Παίξ'": [{ORTH: "Παίξ'", NORM: "παίζω"}],
+    "Αντ'": [{ORTH: "Αντ'", NORM: "αντί"}],
+    "ολ'": [{ORTH: "ολ'", NORM: "όλος"}],
+    "ύστερ'": [{ORTH: "ύστερ'", NORM: "ύστερα"}],
+    "'πρεπε": [{ORTH: "'πρεπε", NORM: "πρέπει"}],
+    "Δύσκολ'": [{ORTH: "Δύσκολ'", NORM: "δύσκολος"}],
+    "'θελα": [{ORTH: "'θελα", NORM: "θέλω"}],
+    "'γραφα": [{ORTH: "'γραφα", NORM: "γράφω"}],
+    "'παιρνα": [{ORTH: "'παιρνα", NORM: "παίρνω"}],
+    "'δειξε": [{ORTH: "'δειξε", NORM: "δείχνω"}],
+    "όμουρφ'": [{ORTH: "όμουρφ'", NORM: "όμορφος"}],
+    "κ'τσή": [{ORTH: "κ'τσή", NORM: "κουτσός"}],
+    "μηδ'": [{ORTH: "μηδ'", NORM: "μήδε"}],
+    "'ξομολογήθηκε": [{ORTH: "'ξομολογήθηκε", NORM: "εξομολογούμαι"}],
+    "'μας": [{ORTH: "'μας", NORM: "εμάς"}],
+    "'ξερες": [{ORTH: "'ξερες", NORM: "ξέρω"}],
+    "έφθασ'": [{ORTH: "έφθασ'", NORM: "φθάνω"}],
+    "εξ'": [{ORTH: "εξ'", NORM: "εκ"}],
+    "δώσ'": [{ORTH: "δώσ'", NORM: "δίνω"}],
+    "τίποτ'": [{ORTH: "τίποτ'", NORM: "τίποτα"}],
+    "Λήξ'": [{ORTH: "Λήξ'", NORM: "λήγω"}],
+    "άσ'": [{ORTH: "άσ'", NORM: "αφήνω"}],
+    "Στ'": [{ORTH: "Στ'", NORM: "στο"}],
+    "Δωσ'": [{ORTH: "Δωσ'", NORM: "δίνω"}],
+    "Βάψ'": [{ORTH: "Βάψ'", NORM: "βάφω"}],
+    "Αλλ'": [{ORTH: "Αλλ'", NORM: "αλλά"}],
+    "Αμ'": [{ORTH: "Αμ'", NORM: "άμα"}],
+    "Αγόρασ'": [{ORTH: "Αγόρασ'", NORM: "αγοράζω"}],
+    "'φύγε": [{ORTH: "'φύγε", NORM: "φεύγω"}],
+    "'φερε": [{ORTH: "'φερε", NORM: "φέρνω"}],
+    "'φαγε": [{ORTH: "'φαγε", NORM: "τρώω"}],
+    "'σπαγαν": [{ORTH: "'σπαγαν", NORM: "σπάω"}],
+    "'σκασε": [{ORTH: "'σκασε", NORM: "σκάω"}],
+    "'σβηνε": [{ORTH: "'σβηνε", NORM: "σβήνω"}],
+    "'ριξε": [{ORTH: "'ριξε", NORM: "ρίχνω"}],
+    "'κλεβε": [{ORTH: "'κλεβε", NORM: "κλέβω"}],
+    "'κει": [{ORTH: "'κει", NORM: "εκεί"}],
+    "'βλεπε": [{ORTH: "'βλεπε", NORM: "βλέπω"}],
+    "'βγαινε": [{ORTH: "'βγαινε", NORM: "βγαίνω"}],
 }
 
 _exc.update(_other_exc)
@@ -134,35 +132,35 @@ for h in range(1, 12 + 1):
     for period in ["π.μ.", "πμ"]:
         _exc[f"{h}{period}"] = [
             {ORTH: f"{h}"},
-            {ORTH: period, LEMMA: "π.μ.", NORM: "π.μ."},
+            {ORTH: period, NORM: "π.μ."},
         ]
 
     for period in ["μ.μ.", "μμ"]:
         _exc[f"{h}{period}"] = [
             {ORTH: f"{h}"},
-            {ORTH: period, LEMMA: "μ.μ.", NORM: "μ.μ."},
+            {ORTH: period, NORM: "μ.μ."},
         ]
 
 for exc_data in [
-    {ORTH: "ΑΓΡ.", LEMMA: "Αγροτικός", NORM: "Αγροτικός"},
-    {ORTH: "Αγ. Γρ.", LEMMA: "Αγία Γραφή", NORM: "Αγία Γραφή"},
-    {ORTH: "Αθ.", LEMMA: "Αθανάσιος", NORM: "Αθανάσιος"},
-    {ORTH: "Αλεξ.", LEMMA: "Αλέξανδρος", NORM: "Αλέξανδρος"},
-    {ORTH: "Απρ.", LEMMA: "Απρίλιος", NORM: "Απρίλιος"},
-    {ORTH: "Αύγ.", LEMMA: "Αύγουστος", NORM: "Αύγουστος"},
-    {ORTH: "Δεκ.", LEMMA: "Δεκέμβριος", NORM: "Δεκέμβριος"},
-    {ORTH: "Δημ.", LEMMA: "Δήμος", NORM: "Δήμος"},
-    {ORTH: "Ιαν.", LEMMA: "Ιανουάριος", NORM: "Ιανουάριος"},
-    {ORTH: "Ιούλ.", LEMMA: "Ιούλιος", NORM: "Ιούλιος"},
-    {ORTH: "Ιούν.", LEMMA: "Ιούνιος", NORM: "Ιούνιος"},
-    {ORTH: "Ιωαν.", LEMMA: "Ιωάννης", NORM: "Ιωάννης"},
-    {ORTH: "Μ. Ασία", LEMMA: "Μικρά Ασία", NORM: "Μικρά Ασία"},
-    {ORTH: "Μάρτ.", LEMMA: "Μάρτιος", NORM: "Μάρτιος"},
-    {ORTH: "Μάρτ'", LEMMA: "Μάρτιος", NORM: "Μάρτιος"},
-    {ORTH: "Νοέμβρ.", LEMMA: "Νοέμβριος", NORM: "Νοέμβριος"},
-    {ORTH: "Οκτ.", LEMMA: "Οκτώβριος", NORM: "Οκτώβριος"},
-    {ORTH: "Σεπτ.", LEMMA: "Σεπτέμβριος", NORM: "Σεπτέμβριος"},
-    {ORTH: "Φεβρ.", LEMMA: "Φεβρουάριος", NORM: "Φεβρουάριος"},
+    {ORTH: "ΑΓΡ.", NORM: "Αγροτικός"},
+    {ORTH: "Αγ. Γρ.", NORM: "Αγία Γραφή"},
+    {ORTH: "Αθ.", NORM: "Αθανάσιος"},
+    {ORTH: "Αλεξ.", NORM: "Αλέξανδρος"},
+    {ORTH: "Απρ.", NORM: "Απρίλιος"},
+    {ORTH: "Αύγ.", NORM: "Αύγουστος"},
+    {ORTH: "Δεκ.", NORM: "Δεκέμβριος"},
+    {ORTH: "Δημ.", NORM: "Δήμος"},
+    {ORTH: "Ιαν.", NORM: "Ιανουάριος"},
+    {ORTH: "Ιούλ.", NORM: "Ιούλιος"},
+    {ORTH: "Ιούν.", NORM: "Ιούνιος"},
+    {ORTH: "Ιωαν.", NORM: "Ιωάννης"},
+    {ORTH: "Μ. Ασία", NORM: "Μικρά Ασία"},
+    {ORTH: "Μάρτ.", NORM: "Μάρτιος"},
+    {ORTH: "Μάρτ'", NORM: "Μάρτιος"},
+    {ORTH: "Νοέμβρ.", NORM: "Νοέμβριος"},
+    {ORTH: "Οκτ.", NORM: "Οκτώβριος"},
+    {ORTH: "Σεπτ.", NORM: "Σεπτέμβριος"},
+    {ORTH: "Φεβρ.", NORM: "Φεβρουάριος"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/en/tokenizer_exceptions.py b/spacy/lang/en/tokenizer_exceptions.py
index 226678430..c210e1a19 100644
--- a/spacy/lang/en/tokenizer_exceptions.py
+++ b/spacy/lang/en/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, TAG, NORM, PRON_LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -28,110 +28,110 @@ _exclude = [
 for pron in ["i"]:
     for orth in [pron, pron.title()]:
         _exc[orth + "'m"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "'m", LEMMA: "be", NORM: "am", TAG: "VBP"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "'m", NORM: "am"},
         ]
 
         _exc[orth + "m"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "m", LEMMA: "be", TAG: "VBP", "tenspect": 1, "number": 1},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "m", "tenspect": 1, "number": 1},
         ]
 
         _exc[orth + "'ma"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "'m", LEMMA: "be", NORM: "am"},
-            {ORTH: "a", LEMMA: "going to", NORM: "gonna"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "'m", NORM: "am"},
+            {ORTH: "a", NORM: "gonna"},
         ]
 
         _exc[orth + "ma"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "m", LEMMA: "be", NORM: "am"},
-            {ORTH: "a", LEMMA: "going to", NORM: "gonna"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "m", NORM: "am"},
+            {ORTH: "a", NORM: "gonna"},
         ]
 
 
 for pron in ["i", "you", "he", "she", "it", "we", "they"]:
     for orth in [pron, pron.title()]:
         _exc[orth + "'ll"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "'ll", LEMMA: "will", NORM: "will", TAG: "MD"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "'ll", NORM: "will"},
         ]
 
         _exc[orth + "ll"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "ll", LEMMA: "will", NORM: "will", TAG: "MD"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "ll", NORM: "will"},
         ]
 
         _exc[orth + "'ll've"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "'ll", LEMMA: "will", NORM: "will", TAG: "MD"},
-            {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "'ll", NORM: "will"},
+            {ORTH: "'ve", NORM: "have"},
         ]
 
         _exc[orth + "llve"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "ll", LEMMA: "will", NORM: "will", TAG: "MD"},
-            {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "ll", NORM: "will"},
+            {ORTH: "ve", NORM: "have"},
         ]
 
         _exc[orth + "'d"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
+            {ORTH: orth, NORM: pron},
             {ORTH: "'d", NORM: "'d"},
         ]
 
         _exc[orth + "d"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
+            {ORTH: orth, NORM: pron},
             {ORTH: "d", NORM: "'d"},
         ]
 
         _exc[orth + "'d've"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "'d", LEMMA: "would", NORM: "would", TAG: "MD"},
-            {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "'d", NORM: "would"},
+            {ORTH: "'ve", NORM: "have"},
         ]
 
         _exc[orth + "dve"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "d", LEMMA: "would", NORM: "would", TAG: "MD"},
-            {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "d", NORM: "would"},
+            {ORTH: "ve", NORM: "have"},
         ]
 
 
 for pron in ["i", "you", "we", "they"]:
     for orth in [pron, pron.title()]:
         _exc[orth + "'ve"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "'ve", NORM: "have"},
         ]
 
         _exc[orth + "ve"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "ve", NORM: "have"},
         ]
 
 
 for pron in ["you", "we", "they"]:
     for orth in [pron, pron.title()]:
         _exc[orth + "'re"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "'re", LEMMA: "be", NORM: "are"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "'re", NORM: "are"},
         ]
 
         _exc[orth + "re"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
-            {ORTH: "re", LEMMA: "be", NORM: "are", TAG: "VBZ"},
+            {ORTH: orth, NORM: pron},
+            {ORTH: "re", NORM: "are"},
         ]
 
 
 for pron in ["he", "she", "it"]:
     for orth in [pron, pron.title()]:
         _exc[orth + "'s"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
+            {ORTH: orth, NORM: pron},
             {ORTH: "'s", NORM: "'s"},
         ]
 
         _exc[orth + "s"] = [
-            {ORTH: orth, LEMMA: PRON_LEMMA, NORM: pron, TAG: "PRP"},
+            {ORTH: orth, NORM: pron},
             {ORTH: "s"},
         ]
 
@@ -153,145 +153,145 @@ for word in [
 ]:
     for orth in [word, word.title()]:
         _exc[orth + "'s"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
+            {ORTH: orth, NORM: word},
             {ORTH: "'s", NORM: "'s"},
         ]
 
-        _exc[orth + "s"] = [{ORTH: orth, LEMMA: word, NORM: word}, {ORTH: "s"}]
+        _exc[orth + "s"] = [{ORTH: orth, NORM: word}, {ORTH: "s"}]
 
         _exc[orth + "'ll"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "'ll", LEMMA: "will", NORM: "will", TAG: "MD"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "'ll", NORM: "will"},
         ]
 
         _exc[orth + "ll"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "ll", LEMMA: "will", NORM: "will", TAG: "MD"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "ll", NORM: "will"},
         ]
 
         _exc[orth + "'ll've"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "'ll", LEMMA: "will", NORM: "will", TAG: "MD"},
-            {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "'ll", NORM: "will"},
+            {ORTH: "'ve", NORM: "have"},
         ]
 
         _exc[orth + "llve"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "ll", LEMMA: "will", NORM: "will", TAG: "MD"},
-            {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "ll", NORM: "will"},
+            {ORTH: "ve", NORM: "have"},
         ]
 
         _exc[orth + "'re"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "'re", LEMMA: "be", NORM: "are"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "'re", NORM: "are"},
         ]
 
         _exc[orth + "re"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "re", LEMMA: "be", NORM: "are"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "re", NORM: "are"},
         ]
 
         _exc[orth + "'ve"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "'ve", LEMMA: "have", TAG: "VB"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "'ve"},
         ]
 
         _exc[orth + "ve"] = [
-            {ORTH: orth, LEMMA: word},
-            {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth},
+            {ORTH: "ve", NORM: "have"},
         ]
 
         _exc[orth + "'d"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
+            {ORTH: orth, NORM: word},
             {ORTH: "'d", NORM: "'d"},
         ]
 
         _exc[orth + "d"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
+            {ORTH: orth, NORM: word},
             {ORTH: "d", NORM: "'d"},
         ]
 
         _exc[orth + "'d've"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "'d", LEMMA: "would", NORM: "would", TAG: "MD"},
-            {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "'d", NORM: "would"},
+            {ORTH: "'ve", NORM: "have"},
         ]
 
         _exc[orth + "dve"] = [
-            {ORTH: orth, LEMMA: word, NORM: word},
-            {ORTH: "d", LEMMA: "would", NORM: "would", TAG: "MD"},
-            {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: orth, NORM: word},
+            {ORTH: "d", NORM: "would"},
+            {ORTH: "ve", NORM: "have"},
         ]
 
 
 # Verbs
 
 for verb_data in [
-    {ORTH: "ca", LEMMA: "can", NORM: "can", TAG: "MD"},
-    {ORTH: "could", NORM: "could", TAG: "MD"},
-    {ORTH: "do", LEMMA: "do", NORM: "do"},
-    {ORTH: "does", LEMMA: "do", NORM: "does"},
-    {ORTH: "did", LEMMA: "do", NORM: "do", TAG: "VBD"},
-    {ORTH: "had", LEMMA: "have", NORM: "have", TAG: "VBD"},
-    {ORTH: "may", NORM: "may", TAG: "MD"},
-    {ORTH: "might", NORM: "might", TAG: "MD"},
-    {ORTH: "must", NORM: "must", TAG: "MD"},
+    {ORTH: "ca", NORM: "can"},
+    {ORTH: "could", NORM: "could"},
+    {ORTH: "do", NORM: "do"},
+    {ORTH: "does", NORM: "does"},
+    {ORTH: "did", NORM: "do"},
+    {ORTH: "had", NORM: "have"},
+    {ORTH: "may", NORM: "may"},
+    {ORTH: "might", NORM: "might"},
+    {ORTH: "must", NORM: "must"},
     {ORTH: "need", NORM: "need"},
-    {ORTH: "ought", NORM: "ought", TAG: "MD"},
-    {ORTH: "sha", LEMMA: "shall", NORM: "shall", TAG: "MD"},
-    {ORTH: "should", NORM: "should", TAG: "MD"},
-    {ORTH: "wo", LEMMA: "will", NORM: "will", TAG: "MD"},
-    {ORTH: "would", NORM: "would", TAG: "MD"},
+    {ORTH: "ought", NORM: "ought"},
+    {ORTH: "sha", NORM: "shall"},
+    {ORTH: "should", NORM: "should"},
+    {ORTH: "wo", NORM: "will"},
+    {ORTH: "would", NORM: "would"},
 ]:
     verb_data_tc = dict(verb_data)
     verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
     for data in [verb_data, verb_data_tc]:
         _exc[data[ORTH] + "n't"] = [
             dict(data),
-            {ORTH: "n't", LEMMA: "not", NORM: "not", TAG: "RB"},
+            {ORTH: "n't", NORM: "not"},
         ]
 
         _exc[data[ORTH] + "nt"] = [
             dict(data),
-            {ORTH: "nt", LEMMA: "not", NORM: "not", TAG: "RB"},
+            {ORTH: "nt", NORM: "not"},
         ]
 
         _exc[data[ORTH] + "n't've"] = [
             dict(data),
-            {ORTH: "n't", LEMMA: "not", NORM: "not", TAG: "RB"},
-            {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: "n't", NORM: "not"},
+            {ORTH: "'ve", NORM: "have"},
         ]
 
         _exc[data[ORTH] + "ntve"] = [
             dict(data),
-            {ORTH: "nt", LEMMA: "not", NORM: "not", TAG: "RB"},
-            {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
+            {ORTH: "nt", NORM: "not"},
+            {ORTH: "ve", NORM: "have"},
         ]
 
 
 for verb_data in [
-    {ORTH: "could", NORM: "could", TAG: "MD"},
-    {ORTH: "might", NORM: "might", TAG: "MD"},
-    {ORTH: "must", NORM: "must", TAG: "MD"},
-    {ORTH: "should", NORM: "should", TAG: "MD"},
-    {ORTH: "would", NORM: "would", TAG: "MD"},
+    {ORTH: "could", NORM: "could"},
+    {ORTH: "might", NORM: "might"},
+    {ORTH: "must", NORM: "must"},
+    {ORTH: "should", NORM: "should"},
+    {ORTH: "would", NORM: "would"},
 ]:
     verb_data_tc = dict(verb_data)
     verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
     for data in [verb_data, verb_data_tc]:
-        _exc[data[ORTH] + "'ve"] = [dict(data), {ORTH: "'ve", LEMMA: "have", TAG: "VB"}]
+        _exc[data[ORTH] + "'ve"] = [dict(data), {ORTH: "'ve"}]
 
-        _exc[data[ORTH] + "ve"] = [dict(data), {ORTH: "ve", LEMMA: "have", TAG: "VB"}]
+        _exc[data[ORTH] + "ve"] = [dict(data), {ORTH: "ve"}]
 
 
 for verb_data in [
-    {ORTH: "ai", LEMMA: "be", TAG: "VBP", "number": 2},
-    {ORTH: "are", LEMMA: "be", NORM: "are", TAG: "VBP", "number": 2},
-    {ORTH: "is", LEMMA: "be", NORM: "is", TAG: "VBZ"},
-    {ORTH: "was", LEMMA: "be", NORM: "was"},
-    {ORTH: "were", LEMMA: "be", NORM: "were"},
+    {ORTH: "ai", "number": 2},
+    {ORTH: "are", NORM: "are", "number": 2},
+    {ORTH: "is", NORM: "is"},
+    {ORTH: "was", NORM: "was"},
+    {ORTH: "were", NORM: "were"},
     {ORTH: "have", NORM: "have"},
-    {ORTH: "has", LEMMA: "have", NORM: "has"},
+    {ORTH: "has", NORM: "has"},
     {ORTH: "dare", NORM: "dare"},
 ]:
     verb_data_tc = dict(verb_data)
@@ -299,24 +299,24 @@ for verb_data in [
     for data in [verb_data, verb_data_tc]:
         _exc[data[ORTH] + "n't"] = [
             dict(data),
-            {ORTH: "n't", LEMMA: "not", NORM: "not", TAG: "RB"},
+            {ORTH: "n't", NORM: "not"},
         ]
 
         _exc[data[ORTH] + "nt"] = [
             dict(data),
-            {ORTH: "nt", LEMMA: "not", NORM: "not", TAG: "RB"},
+            {ORTH: "nt", NORM: "not"},
         ]
 
 
 # Other contractions with trailing apostrophe
 
 for exc_data in [
-    {ORTH: "doin", LEMMA: "do", NORM: "doing"},
-    {ORTH: "goin", LEMMA: "go", NORM: "going"},
-    {ORTH: "nothin", LEMMA: "nothing", NORM: "nothing"},
-    {ORTH: "nuthin", LEMMA: "nothing", NORM: "nothing"},
-    {ORTH: "ol", LEMMA: "old", NORM: "old"},
-    {ORTH: "somethin", LEMMA: "something", NORM: "something"},
+    {ORTH: "doin", NORM: "doing"},
+    {ORTH: "goin", NORM: "going"},
+    {ORTH: "nothin", NORM: "nothing"},
+    {ORTH: "nuthin", NORM: "nothing"},
+    {ORTH: "ol", NORM: "old"},
+    {ORTH: "somethin", NORM: "something"},
 ]:
     exc_data_tc = dict(exc_data)
     exc_data_tc[ORTH] = exc_data_tc[ORTH].title()
@@ -331,9 +331,9 @@ for exc_data in [
 
 for exc_data in [
     {ORTH: "cause", NORM: "because"},
-    {ORTH: "em", LEMMA: PRON_LEMMA, NORM: "them"},
-    {ORTH: "ll", LEMMA: "will", NORM: "will"},
-    {ORTH: "nuff", LEMMA: "enough", NORM: "enough"},
+    {ORTH: "em", NORM: "them"},
+    {ORTH: "ll", NORM: "will"},
+    {ORTH: "nuff", NORM: "enough"},
 ]:
     exc_data_apos = dict(exc_data)
     exc_data_apos[ORTH] = "'" + exc_data_apos[ORTH]
@@ -347,166 +347,131 @@ for h in range(1, 12 + 1):
     for period in ["a.m.", "am"]:
         _exc[f"{h}{period}"] = [
             {ORTH: f"{h}"},
-            {ORTH: period, LEMMA: "a.m.", NORM: "a.m."},
+            {ORTH: period, NORM: "a.m."},
         ]
     for period in ["p.m.", "pm"]:
         _exc[f"{h}{period}"] = [
             {ORTH: f"{h}"},
-            {ORTH: period, LEMMA: "p.m.", NORM: "p.m."},
+            {ORTH: period, NORM: "p.m."},
         ]
 
 
 # Rest
 
 _other_exc = {
-    "y'all": [{ORTH: "y'", LEMMA: PRON_LEMMA, NORM: "you"}, {ORTH: "all"}],
-    "yall": [{ORTH: "y", LEMMA: PRON_LEMMA, NORM: "you"}, {ORTH: "all"}],
-    "how'd'y": [
-        {ORTH: "how", LEMMA: "how"},
-        {ORTH: "'d", LEMMA: "do"},
-        {ORTH: "'y", LEMMA: PRON_LEMMA, NORM: "you"},
-    ],
-    "How'd'y": [
-        {ORTH: "How", LEMMA: "how", NORM: "how"},
-        {ORTH: "'d", LEMMA: "do"},
-        {ORTH: "'y", LEMMA: PRON_LEMMA, NORM: "you"},
-    ],
-    "not've": [
-        {ORTH: "not", LEMMA: "not", TAG: "RB"},
-        {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
-    ],
-    "notve": [
-        {ORTH: "not", LEMMA: "not", TAG: "RB"},
-        {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
-    ],
-    "Not've": [
-        {ORTH: "Not", LEMMA: "not", NORM: "not", TAG: "RB"},
-        {ORTH: "'ve", LEMMA: "have", NORM: "have", TAG: "VB"},
-    ],
-    "Notve": [
-        {ORTH: "Not", LEMMA: "not", NORM: "not", TAG: "RB"},
-        {ORTH: "ve", LEMMA: "have", NORM: "have", TAG: "VB"},
-    ],
-    "cannot": [
-        {ORTH: "can", LEMMA: "can", TAG: "MD"},
-        {ORTH: "not", LEMMA: "not", TAG: "RB"},
-    ],
-    "Cannot": [
-        {ORTH: "Can", LEMMA: "can", NORM: "can", TAG: "MD"},
-        {ORTH: "not", LEMMA: "not", TAG: "RB"},
-    ],
-    "gonna": [
-        {ORTH: "gon", LEMMA: "go", NORM: "going"},
-        {ORTH: "na", LEMMA: "to", NORM: "to"},
-    ],
-    "Gonna": [
-        {ORTH: "Gon", LEMMA: "go", NORM: "going"},
-        {ORTH: "na", LEMMA: "to", NORM: "to"},
-    ],
-    "gotta": [{ORTH: "got"}, {ORTH: "ta", LEMMA: "to", NORM: "to"}],
-    "Gotta": [{ORTH: "Got", NORM: "got"}, {ORTH: "ta", LEMMA: "to", NORM: "to"}],
-    "let's": [{ORTH: "let"}, {ORTH: "'s", LEMMA: PRON_LEMMA, NORM: "us"}],
-    "Let's": [
-        {ORTH: "Let", LEMMA: "let", NORM: "let"},
-        {ORTH: "'s", LEMMA: PRON_LEMMA, NORM: "us"},
-    ],
-    "c'mon": [{ORTH: "c'm", NORM: "come", LEMMA: "come"}, {ORTH: "on"}],
-    "C'mon": [{ORTH: "C'm", NORM: "come", LEMMA: "come"}, {ORTH: "on"}],
+    "y'all": [{ORTH: "y'", NORM: "you"}, {ORTH: "all"}],
+    "yall": [{ORTH: "y", NORM: "you"}, {ORTH: "all"}],
+    "how'd'y": [{ORTH: "how"}, {ORTH: "'d"}, {ORTH: "'y", NORM: "you"}],
+    "How'd'y": [{ORTH: "How", NORM: "how"}, {ORTH: "'d"}, {ORTH: "'y", NORM: "you"}],
+    "not've": [{ORTH: "not"}, {ORTH: "'ve", NORM: "have"}],
+    "notve": [{ORTH: "not"}, {ORTH: "ve", NORM: "have"}],
+    "Not've": [{ORTH: "Not", NORM: "not"}, {ORTH: "'ve", NORM: "have"}],
+    "Notve": [{ORTH: "Not", NORM: "not"}, {ORTH: "ve", NORM: "have"}],
+    "cannot": [{ORTH: "can"}, {ORTH: "not"}],
+    "Cannot": [{ORTH: "Can", NORM: "can"}, {ORTH: "not"}],
+    "gonna": [{ORTH: "gon", NORM: "going"}, {ORTH: "na", NORM: "to"}],
+    "Gonna": [{ORTH: "Gon", NORM: "going"}, {ORTH: "na", NORM: "to"}],
+    "gotta": [{ORTH: "got"}, {ORTH: "ta", NORM: "to"}],
+    "Gotta": [{ORTH: "Got", NORM: "got"}, {ORTH: "ta", NORM: "to"}],
+    "let's": [{ORTH: "let"}, {ORTH: "'s", NORM: "us"}],
+    "Let's": [{ORTH: "Let", NORM: "let"}, {ORTH: "'s", NORM: "us"}],
+    "c'mon": [{ORTH: "c'm", NORM: "come"}, {ORTH: "on"}],
+    "C'mon": [{ORTH: "C'm", NORM: "come"}, {ORTH: "on"}],
 }
 
 _exc.update(_other_exc)
 
 
 for exc_data in [
-    {ORTH: "'S", LEMMA: "'s", NORM: "'s"},
-    {ORTH: "'s", LEMMA: "'s", NORM: "'s"},
-    {ORTH: "\u2018S", LEMMA: "'s", NORM: "'s"},
-    {ORTH: "\u2018s", LEMMA: "'s", NORM: "'s"},
-    {ORTH: "and/or", LEMMA: "and/or", NORM: "and/or", TAG: "CC"},
-    {ORTH: "w/o", LEMMA: "without", NORM: "without"},
-    {ORTH: "'re", LEMMA: "be", NORM: "are"},
-    {ORTH: "'Cause", LEMMA: "because", NORM: "because"},
-    {ORTH: "'cause", LEMMA: "because", NORM: "because"},
-    {ORTH: "'cos", LEMMA: "because", NORM: "because"},
-    {ORTH: "'Cos", LEMMA: "because", NORM: "because"},
-    {ORTH: "'coz", LEMMA: "because", NORM: "because"},
-    {ORTH: "'Coz", LEMMA: "because", NORM: "because"},
-    {ORTH: "'cuz", LEMMA: "because", NORM: "because"},
-    {ORTH: "'Cuz", LEMMA: "because", NORM: "because"},
-    {ORTH: "'bout", LEMMA: "about", NORM: "about"},
-    {ORTH: "ma'am", LEMMA: "madam", NORM: "madam"},
-    {ORTH: "Ma'am", LEMMA: "madam", NORM: "madam"},
-    {ORTH: "o'clock", LEMMA: "o'clock", NORM: "o'clock"},
-    {ORTH: "O'clock", LEMMA: "o'clock", NORM: "o'clock"},
-    {ORTH: "lovin'", LEMMA: "love", NORM: "loving"},
-    {ORTH: "Lovin'", LEMMA: "love", NORM: "loving"},
-    {ORTH: "lovin", LEMMA: "love", NORM: "loving"},
-    {ORTH: "Lovin", LEMMA: "love", NORM: "loving"},
-    {ORTH: "havin'", LEMMA: "have", NORM: "having"},
-    {ORTH: "Havin'", LEMMA: "have", NORM: "having"},
-    {ORTH: "havin", LEMMA: "have", NORM: "having"},
-    {ORTH: "Havin", LEMMA: "have", NORM: "having"},
-    {ORTH: "doin'", LEMMA: "do", NORM: "doing"},
-    {ORTH: "Doin'", LEMMA: "do", NORM: "doing"},
-    {ORTH: "doin", LEMMA: "do", NORM: "doing"},
-    {ORTH: "Doin", LEMMA: "do", NORM: "doing"},
-    {ORTH: "goin'", LEMMA: "go", NORM: "going"},
-    {ORTH: "Goin'", LEMMA: "go", NORM: "going"},
-    {ORTH: "goin", LEMMA: "go", NORM: "going"},
-    {ORTH: "Goin", LEMMA: "go", NORM: "going"},
-    {ORTH: "Mt.", LEMMA: "Mount", NORM: "Mount"},
-    {ORTH: "Ak.", LEMMA: "Alaska", NORM: "Alaska"},
-    {ORTH: "Ala.", LEMMA: "Alabama", NORM: "Alabama"},
-    {ORTH: "Apr.", LEMMA: "April", NORM: "April"},
-    {ORTH: "Ariz.", LEMMA: "Arizona", NORM: "Arizona"},
-    {ORTH: "Ark.", LEMMA: "Arkansas", NORM: "Arkansas"},
-    {ORTH: "Aug.", LEMMA: "August", NORM: "August"},
-    {ORTH: "Calif.", LEMMA: "California", NORM: "California"},
-    {ORTH: "Colo.", LEMMA: "Colorado", NORM: "Colorado"},
-    {ORTH: "Conn.", LEMMA: "Connecticut", NORM: "Connecticut"},
-    {ORTH: "Dec.", LEMMA: "December", NORM: "December"},
-    {ORTH: "Del.", LEMMA: "Delaware", NORM: "Delaware"},
-    {ORTH: "Feb.", LEMMA: "February", NORM: "February"},
-    {ORTH: "Fla.", LEMMA: "Florida", NORM: "Florida"},
-    {ORTH: "Ga.", LEMMA: "Georgia", NORM: "Georgia"},
-    {ORTH: "Ia.", LEMMA: "Iowa", NORM: "Iowa"},
-    {ORTH: "Id.", LEMMA: "Idaho", NORM: "Idaho"},
-    {ORTH: "Ill.", LEMMA: "Illinois", NORM: "Illinois"},
-    {ORTH: "Ind.", LEMMA: "Indiana", NORM: "Indiana"},
-    {ORTH: "Jan.", LEMMA: "January", NORM: "January"},
-    {ORTH: "Jul.", LEMMA: "July", NORM: "July"},
-    {ORTH: "Jun.", LEMMA: "June", NORM: "June"},
-    {ORTH: "Kan.", LEMMA: "Kansas", NORM: "Kansas"},
-    {ORTH: "Kans.", LEMMA: "Kansas", NORM: "Kansas"},
-    {ORTH: "Ky.", LEMMA: "Kentucky", NORM: "Kentucky"},
-    {ORTH: "La.", LEMMA: "Louisiana", NORM: "Louisiana"},
-    {ORTH: "Mar.", LEMMA: "March", NORM: "March"},
-    {ORTH: "Mass.", LEMMA: "Massachusetts", NORM: "Massachusetts"},
-    {ORTH: "May.", LEMMA: "May", NORM: "May"},
-    {ORTH: "Mich.", LEMMA: "Michigan", NORM: "Michigan"},
-    {ORTH: "Minn.", LEMMA: "Minnesota", NORM: "Minnesota"},
-    {ORTH: "Miss.", LEMMA: "Mississippi", NORM: "Mississippi"},
-    {ORTH: "N.C.", LEMMA: "North Carolina", NORM: "North Carolina"},
-    {ORTH: "N.D.", LEMMA: "North Dakota", NORM: "North Dakota"},
-    {ORTH: "N.H.", LEMMA: "New Hampshire", NORM: "New Hampshire"},
-    {ORTH: "N.J.", LEMMA: "New Jersey", NORM: "New Jersey"},
-    {ORTH: "N.M.", LEMMA: "New Mexico", NORM: "New Mexico"},
-    {ORTH: "N.Y.", LEMMA: "New York", NORM: "New York"},
-    {ORTH: "Neb.", LEMMA: "Nebraska", NORM: "Nebraska"},
-    {ORTH: "Nebr.", LEMMA: "Nebraska", NORM: "Nebraska"},
-    {ORTH: "Nev.", LEMMA: "Nevada", NORM: "Nevada"},
-    {ORTH: "Nov.", LEMMA: "November", NORM: "November"},
-    {ORTH: "Oct.", LEMMA: "October", NORM: "October"},
-    {ORTH: "Okla.", LEMMA: "Oklahoma", NORM: "Oklahoma"},
-    {ORTH: "Ore.", LEMMA: "Oregon", NORM: "Oregon"},
-    {ORTH: "Pa.", LEMMA: "Pennsylvania", NORM: "Pennsylvania"},
-    {ORTH: "S.C.", LEMMA: "South Carolina", NORM: "South Carolina"},
-    {ORTH: "Sep.", LEMMA: "September", NORM: "September"},
-    {ORTH: "Sept.", LEMMA: "September", NORM: "September"},
-    {ORTH: "Tenn.", LEMMA: "Tennessee", NORM: "Tennessee"},
-    {ORTH: "Va.", LEMMA: "Virginia", NORM: "Virginia"},
-    {ORTH: "Wash.", LEMMA: "Washington", NORM: "Washington"},
-    {ORTH: "Wis.", LEMMA: "Wisconsin", NORM: "Wisconsin"},
+    {ORTH: "'S", NORM: "'s"},
+    {ORTH: "'s", NORM: "'s"},
+    {ORTH: "\u2018S", NORM: "'s"},
+    {ORTH: "\u2018s", NORM: "'s"},
+    {ORTH: "and/or", NORM: "and/or"},
+    {ORTH: "w/o", NORM: "without"},
+    {ORTH: "'re", NORM: "are"},
+    {ORTH: "'Cause", NORM: "because"},
+    {ORTH: "'cause", NORM: "because"},
+    {ORTH: "'cos", NORM: "because"},
+    {ORTH: "'Cos", NORM: "because"},
+    {ORTH: "'coz", NORM: "because"},
+    {ORTH: "'Coz", NORM: "because"},
+    {ORTH: "'cuz", NORM: "because"},
+    {ORTH: "'Cuz", NORM: "because"},
+    {ORTH: "'bout", NORM: "about"},
+    {ORTH: "ma'am", NORM: "madam"},
+    {ORTH: "Ma'am", NORM: "madam"},
+    {ORTH: "o'clock", NORM: "o'clock"},
+    {ORTH: "O'clock", NORM: "o'clock"},
+    {ORTH: "lovin'", NORM: "loving"},
+    {ORTH: "Lovin'", NORM: "loving"},
+    {ORTH: "lovin", NORM: "loving"},
+    {ORTH: "Lovin", NORM: "loving"},
+    {ORTH: "havin'", NORM: "having"},
+    {ORTH: "Havin'", NORM: "having"},
+    {ORTH: "havin", NORM: "having"},
+    {ORTH: "Havin", NORM: "having"},
+    {ORTH: "doin'", NORM: "doing"},
+    {ORTH: "Doin'", NORM: "doing"},
+    {ORTH: "doin", NORM: "doing"},
+    {ORTH: "Doin", NORM: "doing"},
+    {ORTH: "goin'", NORM: "going"},
+    {ORTH: "Goin'", NORM: "going"},
+    {ORTH: "goin", NORM: "going"},
+    {ORTH: "Goin", NORM: "going"},
+    {ORTH: "Mt.", NORM: "Mount"},
+    {ORTH: "Ak.", NORM: "Alaska"},
+    {ORTH: "Ala.", NORM: "Alabama"},
+    {ORTH: "Apr.", NORM: "April"},
+    {ORTH: "Ariz.", NORM: "Arizona"},
+    {ORTH: "Ark.", NORM: "Arkansas"},
+    {ORTH: "Aug.", NORM: "August"},
+    {ORTH: "Calif.", NORM: "California"},
+    {ORTH: "Colo.", NORM: "Colorado"},
+    {ORTH: "Conn.", NORM: "Connecticut"},
+    {ORTH: "Dec.", NORM: "December"},
+    {ORTH: "Del.", NORM: "Delaware"},
+    {ORTH: "Feb.", NORM: "February"},
+    {ORTH: "Fla.", NORM: "Florida"},
+    {ORTH: "Ga.", NORM: "Georgia"},
+    {ORTH: "Ia.", NORM: "Iowa"},
+    {ORTH: "Id.", NORM: "Idaho"},
+    {ORTH: "Ill.", NORM: "Illinois"},
+    {ORTH: "Ind.", NORM: "Indiana"},
+    {ORTH: "Jan.", NORM: "January"},
+    {ORTH: "Jul.", NORM: "July"},
+    {ORTH: "Jun.", NORM: "June"},
+    {ORTH: "Kan.", NORM: "Kansas"},
+    {ORTH: "Kans.", NORM: "Kansas"},
+    {ORTH: "Ky.", NORM: "Kentucky"},
+    {ORTH: "La.", NORM: "Louisiana"},
+    {ORTH: "Mar.", NORM: "March"},
+    {ORTH: "Mass.", NORM: "Massachusetts"},
+    {ORTH: "May.", NORM: "May"},
+    {ORTH: "Mich.", NORM: "Michigan"},
+    {ORTH: "Minn.", NORM: "Minnesota"},
+    {ORTH: "Miss.", NORM: "Mississippi"},
+    {ORTH: "N.C.", NORM: "North Carolina"},
+    {ORTH: "N.D.", NORM: "North Dakota"},
+    {ORTH: "N.H.", NORM: "New Hampshire"},
+    {ORTH: "N.J.", NORM: "New Jersey"},
+    {ORTH: "N.M.", NORM: "New Mexico"},
+    {ORTH: "N.Y.", NORM: "New York"},
+    {ORTH: "Neb.", NORM: "Nebraska"},
+    {ORTH: "Nebr.", NORM: "Nebraska"},
+    {ORTH: "Nev.", NORM: "Nevada"},
+    {ORTH: "Nov.", NORM: "November"},
+    {ORTH: "Oct.", NORM: "October"},
+    {ORTH: "Okla.", NORM: "Oklahoma"},
+    {ORTH: "Ore.", NORM: "Oregon"},
+    {ORTH: "Pa.", NORM: "Pennsylvania"},
+    {ORTH: "S.C.", NORM: "South Carolina"},
+    {ORTH: "Sep.", NORM: "September"},
+    {ORTH: "Sept.", NORM: "September"},
+    {ORTH: "Tenn.", NORM: "Tennessee"},
+    {ORTH: "Va.", NORM: "Virginia"},
+    {ORTH: "Wash.", NORM: "Washington"},
+    {ORTH: "Wis.", NORM: "Wisconsin"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/es/tokenizer_exceptions.py b/spacy/lang/es/tokenizer_exceptions.py
index 63124578e..fbfe75545 100644
--- a/spacy/lang/es/tokenizer_exceptions.py
+++ b/spacy/lang/es/tokenizer_exceptions.py
@@ -1,27 +1,27 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM, PRON_LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
 _exc = {
-    "pal": [{ORTH: "pa", LEMMA: "para"}, {ORTH: "l", LEMMA: "el", NORM: "el"}],
+    "pal": [{ORTH: "pa"}, {ORTH: "l", NORM: "el"}],
 }
 
 
 for exc_data in [
-    {ORTH: "n°", LEMMA: "número"},
-    {ORTH: "°C", LEMMA: "grados Celcius"},
-    {ORTH: "aprox.", LEMMA: "aproximadamente"},
-    {ORTH: "dna.", LEMMA: "docena"},
-    {ORTH: "dpto.", LEMMA: "departamento"},
-    {ORTH: "ej.", LEMMA: "ejemplo"},
-    {ORTH: "esq.", LEMMA: "esquina"},
-    {ORTH: "pág.", LEMMA: "página"},
-    {ORTH: "p.ej.", LEMMA: "por ejemplo"},
-    {ORTH: "Ud.", LEMMA: PRON_LEMMA, NORM: "usted"},
-    {ORTH: "Vd.", LEMMA: PRON_LEMMA, NORM: "usted"},
-    {ORTH: "Uds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
-    {ORTH: "Vds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
+    {ORTH: "n°"},
+    {ORTH: "°C"},
+    {ORTH: "aprox."},
+    {ORTH: "dna."},
+    {ORTH: "dpto."},
+    {ORTH: "ej."},
+    {ORTH: "esq."},
+    {ORTH: "pág."},
+    {ORTH: "p.ej."},
+    {ORTH: "Ud.", NORM: "usted"},
+    {ORTH: "Vd.", NORM: "usted"},
+    {ORTH: "Uds.", NORM: "ustedes"},
+    {ORTH: "Vds.", NORM: "ustedes"},
     {ORTH: "vol.", NORM: "volúmen"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
@@ -29,14 +29,14 @@ for exc_data in [
 
 # Times
 
-_exc["12m."] = [{ORTH: "12"}, {ORTH: "m.", LEMMA: "p.m."}]
+_exc["12m."] = [{ORTH: "12"}, {ORTH: "m."}]
 
 
 for h in range(1, 12 + 1):
     for period in ["a.m.", "am"]:
-        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, LEMMA: "a.m."}]
+        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period}]
     for period in ["p.m.", "pm"]:
-        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period, LEMMA: "p.m."}]
+        _exc[f"{h}{period}"] = [{ORTH: f"{h}"}, {ORTH: period}]
 
 
 for orth in [
diff --git a/spacy/lang/fa/tokenizer_exceptions.py b/spacy/lang/fa/tokenizer_exceptions.py
index db9e3f6fc..30df798ab 100644
--- a/spacy/lang/fa/tokenizer_exceptions.py
+++ b/spacy/lang/fa/tokenizer_exceptions.py
@@ -1,2753 +1,747 @@
-from ...symbols import ORTH, LEMMA, TAG, NORM
+from ...symbols import ORTH, NORM
 
 
-_exc = {
-    ".ق ": [{LEMMA: "قمری", ORTH: ".ق "}],
-    ".م": [{LEMMA: "میلادی", ORTH: ".م"}],
-    ".هـ": [{LEMMA: "هجری", ORTH: ".هـ"}],
-    "ب.م": [{LEMMA: "بعد از میلاد", ORTH: "ب.م"}],
-    "ق.م": [{LEMMA: "قبل از میلاد", ORTH: "ق.م"}],
+TOKENIZER_EXCEPTIONS = {
+    ".ق ": [{ORTH: ".ق "}],
+    ".م": [{ORTH: ".م"}],
+    ".هـ": [{ORTH: ".هـ"}],
+    "ب.م": [{ORTH: "ب.م"}],
+    "ق.م": [{ORTH: "ق.م"}],
+    "آبرویت": [{ORTH: "آبروی", NORM: "آبروی"}, {ORTH: "ت", NORM: "ت"}],
+    "آب‌نباتش": [{ORTH: "آب‌نبات", NORM: "آب‌نبات"}, {ORTH: "ش", NORM: "ش"}],
+    "آثارش": [{ORTH: "آثار", NORM: "آثار"}, {ORTH: "ش", NORM: "ش"}],
+    "آخرش": [{ORTH: "آخر", NORM: "آخر"}, {ORTH: "ش", NORM: "ش"}],
+    "آدمهاست": [{ORTH: "آدمها", NORM: "آدمها"}, {ORTH: "ست", NORM: "ست"}],
+    "آرزومندیم": [{ORTH: "آرزومند", NORM: "آرزومند"}, {ORTH: "یم", NORM: "یم"}],
+    "آزادند": [{ORTH: "آزاد", NORM: "آزاد"}, {ORTH: "ند", NORM: "ند"}],
+    "آسیب‌پذیرند": [{ORTH: "آسیب‌پذیر", NORM: "آسیب‌پذیر"}, {ORTH: "ند", NORM: "ند"}],
+    "آفریده‌اند": [{ORTH: "آفریده‌", NORM: "آفریده‌"}, {ORTH: "اند", NORM: "اند"}],
+    "آمدنش": [{ORTH: "آمدن", NORM: "آمدن"}, {ORTH: "ش", NORM: "ش"}],
+    "آمریکاست": [{ORTH: "آمریکا", NORM: "آمریکا"}, {ORTH: "ست", NORM: "ست"}],
+    "آنجاست": [{ORTH: "آنجا", NORM: "آنجا"}, {ORTH: "ست", NORM: "ست"}],
+    "آنست": [{ORTH: "آن", NORM: "آن"}, {ORTH: "ست", NORM: "ست"}],
+    "آنند": [{ORTH: "آن", NORM: "آن"}, {ORTH: "ند", NORM: "ند"}],
+    "آن‌هاست": [{ORTH: "آن‌ها", NORM: "آن‌ها"}, {ORTH: "ست", NORM: "ست"}],
+    "آپاداناست": [{ORTH: "آپادانا", NORM: "آپادانا"}, {ORTH: "ست", NORM: "ست"}],
+    "اجتماعی‌مان": [{ORTH: "اجتماعی‌", NORM: "اجتماعی‌"}, {ORTH: "مان", NORM: "مان"}],
+    "اجدادت": [{ORTH: "اجداد", NORM: "اجداد"}, {ORTH: "ت", NORM: "ت"}],
+    "اجدادش": [{ORTH: "اجداد", NORM: "اجداد"}, {ORTH: "ش", NORM: "ش"}],
+    "اجدادی‌شان": [{ORTH: "اجدادی‌", NORM: "اجدادی‌"}, {ORTH: "شان", NORM: "شان"}],
+    "اجراست": [{ORTH: "اجرا", NORM: "اجرا"}, {ORTH: "ست", NORM: "ست"}],
+    "اختیارش": [{ORTH: "اختیار", NORM: "اختیار"}, {ORTH: "ش", NORM: "ش"}],
+    "اخلاقشان": [{ORTH: "اخلاق", NORM: "اخلاق"}, {ORTH: "شان", NORM: "شان"}],
+    "ادعایمان": [{ORTH: "ادعای", NORM: "ادعای"}, {ORTH: "مان", NORM: "مان"}],
+    "اذیتش": [{ORTH: "اذیت", NORM: "اذیت"}, {ORTH: "ش", NORM: "ش"}],
+    "اراده‌اش": [{ORTH: "اراده‌", NORM: "اراده‌"}, {ORTH: "اش", NORM: "اش"}],
+    "ارتباطش": [{ORTH: "ارتباط", NORM: "ارتباط"}, {ORTH: "ش", NORM: "ش"}],
+    "ارتباطمان": [{ORTH: "ارتباط", NORM: "ارتباط"}, {ORTH: "مان", NORM: "مان"}],
+    "ارزشهاست": [{ORTH: "ارزشها", NORM: "ارزشها"}, {ORTH: "ست", NORM: "ست"}],
+    "ارزی‌اش": [{ORTH: "ارزی‌", NORM: "ارزی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "اره‌اش": [{ORTH: "اره‌", NORM: "اره‌"}, {ORTH: "اش", NORM: "اش"}],
+    "ازش": [{ORTH: "از", NORM: "از"}, {ORTH: "ش", NORM: "ش"}],
+    "ازین": [{ORTH: "از", NORM: "از"}, {ORTH: "ین", NORM: "ین"}],
+    "ازین‌هاست": [
+        {ORTH: "از", NORM: "از"},
+        {ORTH: "ین‌ها", NORM: "ین‌ها"},
+        {ORTH: "ست", NORM: "ست"},
+    ],
+    "استخوانند": [{ORTH: "استخوان", NORM: "استخوان"}, {ORTH: "ند", NORM: "ند"}],
+    "اسلامند": [{ORTH: "اسلام", NORM: "اسلام"}, {ORTH: "ند", NORM: "ند"}],
+    "اسلامی‌اند": [{ORTH: "اسلامی‌", NORM: "اسلامی‌"}, {ORTH: "اند", NORM: "اند"}],
+    "اسلحه‌هایشان": [
+        {ORTH: "اسلحه‌های", NORM: "اسلحه‌های"},
+        {ORTH: "شان", NORM: "شان"},
+    ],
+    "اسمت": [{ORTH: "اسم", NORM: "اسم"}, {ORTH: "ت", NORM: "ت"}],
+    "اسمش": [{ORTH: "اسم", NORM: "اسم"}, {ORTH: "ش", NORM: "ش"}],
+    "اشتباهند": [{ORTH: "اشتباه", NORM: "اشتباه"}, {ORTH: "ند", NORM: "ند"}],
+    "اصلش": [{ORTH: "اصل", NORM: "اصل"}, {ORTH: "ش", NORM: "ش"}],
+    "اطاقش": [{ORTH: "اطاق", NORM: "اطاق"}, {ORTH: "ش", NORM: "ش"}],
+    "اعتقادند": [{ORTH: "اعتقاد", NORM: "اعتقاد"}, {ORTH: "ند", NORM: "ند"}],
+    "اعلایش": [{ORTH: "اعلای", NORM: "اعلای"}, {ORTH: "ش", NORM: "ش"}],
+    "افتراست": [{ORTH: "افترا", NORM: "افترا"}, {ORTH: "ست", NORM: "ست"}],
+    "افطارت": [{ORTH: "افطار", NORM: "افطار"}, {ORTH: "ت", NORM: "ت"}],
+    "اقوامش": [{ORTH: "اقوام", NORM: "اقوام"}, {ORTH: "ش", NORM: "ش"}],
+    "امروزیش": [{ORTH: "امروزی", NORM: "امروزی"}, {ORTH: "ش", NORM: "ش"}],
+    "اموالش": [{ORTH: "اموال", NORM: "اموال"}, {ORTH: "ش", NORM: "ش"}],
+    "امیدوارند": [{ORTH: "امیدوار", NORM: "امیدوار"}, {ORTH: "ند", NORM: "ند"}],
+    "امیدواریم": [{ORTH: "امیدوار", NORM: "امیدوار"}, {ORTH: "یم", NORM: "یم"}],
+    "انتخابهایم": [{ORTH: "انتخابها", NORM: "انتخابها"}, {ORTH: "یم", NORM: "یم"}],
+    "انتظارم": [{ORTH: "انتظار", NORM: "انتظار"}, {ORTH: "م", NORM: "م"}],
+    "انجمنم": [{ORTH: "انجمن", NORM: "انجمن"}, {ORTH: "م", NORM: "م"}],
+    "اندرش": [{ORTH: "اندر", NORM: "اندر"}, {ORTH: "ش", NORM: "ش"}],
+    "انشایش": [{ORTH: "انشای", NORM: "انشای"}, {ORTH: "ش", NORM: "ش"}],
+    "انگشتشان": [{ORTH: "انگشت", NORM: "انگشت"}, {ORTH: "شان", NORM: "شان"}],
+    "انگشتهایش": [{ORTH: "انگشتهای", NORM: "انگشتهای"}, {ORTH: "ش", NORM: "ش"}],
+    "اهمیتشان": [{ORTH: "اهمیت", NORM: "اهمیت"}, {ORTH: "شان", NORM: "شان"}],
+    "اهمیتند": [{ORTH: "اهمیت", NORM: "اهمیت"}, {ORTH: "ند", NORM: "ند"}],
+    "اوایلش": [{ORTH: "اوایل", NORM: "اوایل"}, {ORTH: "ش", NORM: "ش"}],
+    "اوست": [{ORTH: "او", NORM: "او"}, {ORTH: "ست", NORM: "ست"}],
+    "اولش": [{ORTH: "اول", NORM: "اول"}, {ORTH: "ش", NORM: "ش"}],
+    "اولشان": [{ORTH: "اول", NORM: "اول"}, {ORTH: "شان", NORM: "شان"}],
+    "اولم": [{ORTH: "اول", NORM: "اول"}, {ORTH: "م", NORM: "م"}],
+    "اکثرشان": [{ORTH: "اکثر", NORM: "اکثر"}, {ORTH: "شان", NORM: "شان"}],
+    "ایتالیاست": [{ORTH: "ایتالیا", NORM: "ایتالیا"}, {ORTH: "ست", NORM: "ست"}],
+    "ایرانی‌اش": [{ORTH: "ایرانی‌", NORM: "ایرانی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "اینجاست": [{ORTH: "اینجا", NORM: "اینجا"}, {ORTH: "ست", NORM: "ست"}],
+    "این‌هاست": [{ORTH: "این‌ها", NORM: "این‌ها"}, {ORTH: "ست", NORM: "ست"}],
+    "بابات": [{ORTH: "بابا", NORM: "بابا"}, {ORTH: "ت", NORM: "ت"}],
+    "بارش": [{ORTH: "بار", NORM: "بار"}, {ORTH: "ش", NORM: "ش"}],
+    "بازیگرانش": [{ORTH: "بازیگران", NORM: "بازیگران"}, {ORTH: "ش", NORM: "ش"}],
+    "بازیگرمان": [{ORTH: "بازیگر", NORM: "بازیگر"}, {ORTH: "مان", NORM: "مان"}],
+    "بازیگرهایم": [{ORTH: "بازیگرها", NORM: "بازیگرها"}, {ORTH: "یم", NORM: "یم"}],
+    "بازی‌اش": [{ORTH: "بازی‌", NORM: "بازی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "بالاست": [{ORTH: "بالا", NORM: "بالا"}, {ORTH: "ست", NORM: "ست"}],
+    "باورند": [{ORTH: "باور", NORM: "باور"}, {ORTH: "ند", NORM: "ند"}],
+    "بجاست": [{ORTH: "بجا", NORM: "بجا"}, {ORTH: "ست", NORM: "ست"}],
+    "بدان": [{ORTH: "ب", NORM: "ب"}, {ORTH: "دان", NORM: "دان"}],
+    "بدش": [{ORTH: "بد", NORM: "بد"}, {ORTH: "ش", NORM: "ش"}],
+    "بدشان": [{ORTH: "بد", NORM: "بد"}, {ORTH: "شان", NORM: "شان"}],
+    "بدنم": [{ORTH: "بدن", NORM: "بدن"}, {ORTH: "م", NORM: "م"}],
+    "بدهی‌ات": [{ORTH: "بدهی‌", NORM: "بدهی‌"}, {ORTH: "ات", NORM: "ات"}],
+    "بدین": [{ORTH: "ب", NORM: "ب"}, {ORTH: "دین", NORM: "دین"}],
+    "برابرش": [{ORTH: "برابر", NORM: "برابر"}, {ORTH: "ش", NORM: "ش"}],
+    "برادرت": [{ORTH: "برادر", NORM: "برادر"}, {ORTH: "ت", NORM: "ت"}],
+    "برادرش": [{ORTH: "برادر", NORM: "برادر"}, {ORTH: "ش", NORM: "ش"}],
+    "برایت": [{ORTH: "برای", NORM: "برای"}, {ORTH: "ت", NORM: "ت"}],
+    "برایتان": [{ORTH: "برای", NORM: "برای"}, {ORTH: "تان", NORM: "تان"}],
+    "برایش": [{ORTH: "برای", NORM: "برای"}, {ORTH: "ش", NORM: "ش"}],
+    "برایشان": [{ORTH: "برای", NORM: "برای"}, {ORTH: "شان", NORM: "شان"}],
+    "برایم": [{ORTH: "برای", NORM: "برای"}, {ORTH: "م", NORM: "م"}],
+    "برایمان": [{ORTH: "برای", NORM: "برای"}, {ORTH: "مان", NORM: "مان"}],
+    "برخوردارند": [{ORTH: "برخوردار", NORM: "برخوردار"}, {ORTH: "ند", NORM: "ند"}],
+    "برنامه‌سازهاست": [
+        {ORTH: "برنامه‌سازها", NORM: "برنامه‌سازها"},
+        {ORTH: "ست", NORM: "ست"},
+    ],
+    "برهمش": [{ORTH: "برهم", NORM: "برهم"}, {ORTH: "ش", NORM: "ش"}],
+    "برهنه‌اش": [{ORTH: "برهنه‌", NORM: "برهنه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "برگهایش": [{ORTH: "برگها", NORM: "برگها"}, {ORTH: "یش", NORM: "یش"}],
+    "برین": [{ORTH: "بر", NORM: "بر"}, {ORTH: "ین", NORM: "ین"}],
+    "بزرگش": [{ORTH: "بزرگ", NORM: "بزرگ"}, {ORTH: "ش", NORM: "ش"}],
+    "بزرگ‌تری": [{ORTH: "بزرگ‌تر", NORM: "بزرگ‌تر"}, {ORTH: "ی", NORM: "ی"}],
+    "بساطش": [{ORTH: "بساط", NORM: "بساط"}, {ORTH: "ش", NORM: "ش"}],
+    "بعدش": [{ORTH: "بعد", NORM: "بعد"}, {ORTH: "ش", NORM: "ش"}],
+    "بعضیهایشان": [{ORTH: "بعضیهای", NORM: "بعضیهای"}, {ORTH: "شان", NORM: "شان"}],
+    "بعضی‌شان": [{ORTH: "بعضی", NORM: "بعضی"}, {ORTH: "‌شان", NORM: "شان"}],
+    "بقیه‌اش": [{ORTH: "بقیه‌", NORM: "بقیه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "بلندش": [{ORTH: "بلند", NORM: "بلند"}, {ORTH: "ش", NORM: "ش"}],
+    "بناگوشش": [{ORTH: "بناگوش", NORM: "بناگوش"}, {ORTH: "ش", NORM: "ش"}],
+    "بنظرم": [
+        {ORTH: "ب", NORM: "ب"},
+        {ORTH: "نظر", NORM: "نظر"},
+        {ORTH: "م", NORM: "م"},
+    ],
+    "بهت": [{ORTH: "به", NORM: "به"}, {ORTH: "ت", NORM: "ت"}],
+    "بهترش": [{ORTH: "بهتر", NORM: "بهتر"}, {ORTH: "ش", NORM: "ش"}],
+    "بهترم": [{ORTH: "بهتر", NORM: "بهتر"}, {ORTH: "م", NORM: "م"}],
+    "بهتری": [{ORTH: "بهتر", NORM: "بهتر"}, {ORTH: "ی", NORM: "ی"}],
+    "بهش": [{ORTH: "به", NORM: "به"}, {ORTH: "ش", NORM: "ش"}],
+    "به‌شان": [{ORTH: "به‌", NORM: "به‌"}, {ORTH: "شان", NORM: "شان"}],
+    "بودمش": [{ORTH: "بودم", NORM: "بودم"}, {ORTH: "ش", NORM: "ش"}],
+    "بودنش": [{ORTH: "بودن", NORM: "بودن"}, {ORTH: "ش", NORM: "ش"}],
+    "بودن‌شان": [{ORTH: "بودن‌", NORM: "بودن‌"}, {ORTH: "شان", NORM: "شان"}],
+    "بوستانش": [{ORTH: "بوستان", NORM: "بوستان"}, {ORTH: "ش", NORM: "ش"}],
+    "بویش": [{ORTH: "بو", NORM: "بو"}, {ORTH: "یش", NORM: "یش"}],
+    "بچه‌اش": [{ORTH: "بچه‌", NORM: "بچه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "بچه‌م": [{ORTH: "بچه‌", NORM: "بچه‌"}, {ORTH: "م", NORM: "م"}],
+    "بچه‌هایش": [{ORTH: "بچه‌های", NORM: "بچه‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "بیانیه‌شان": [{ORTH: "بیانیه‌", NORM: "بیانیه‌"}, {ORTH: "شان", NORM: "شان"}],
+    "بیدارم": [{ORTH: "بیدار", NORM: "بیدار"}, {ORTH: "م", NORM: "م"}],
+    "بیناتری": [{ORTH: "بیناتر", NORM: "بیناتر"}, {ORTH: "ی", NORM: "ی"}],
+    "بی‌اطلاعند": [{ORTH: "بی‌اطلاع", NORM: "بی‌اطلاع"}, {ORTH: "ند", NORM: "ند"}],
+    "بی‌اطلاعید": [{ORTH: "بی‌اطلاع", NORM: "بی‌اطلاع"}, {ORTH: "ید", NORM: "ید"}],
+    "بی‌بهره‌اند": [{ORTH: "بی‌بهره‌", NORM: "بی‌بهره‌"}, {ORTH: "اند", NORM: "اند"}],
+    "بی‌تفاوتند": [{ORTH: "بی‌تفاوت", NORM: "بی‌تفاوت"}, {ORTH: "ند", NORM: "ند"}],
+    "بی‌حسابش": [{ORTH: "بی‌حساب", NORM: "بی‌حساب"}, {ORTH: "ش", NORM: "ش"}],
+    "بی‌نیش": [{ORTH: "بی‌نی", NORM: "بی‌نی"}, {ORTH: "ش", NORM: "ش"}],
+    "تجربه‌هایم": [{ORTH: "تجربه‌ها", NORM: "تجربه‌ها"}, {ORTH: "یم", NORM: "یم"}],
+    "تحریم‌هاست": [{ORTH: "تحریم‌ها", NORM: "تحریم‌ها"}, {ORTH: "ست", NORM: "ست"}],
+    "تحولند": [{ORTH: "تحول", NORM: "تحول"}, {ORTH: "ند", NORM: "ند"}],
+    "تخیلی‌اش": [{ORTH: "تخیلی‌", NORM: "تخیلی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "ترا": [{ORTH: "ت", NORM: "ت"}, {ORTH: "را", NORM: "را"}],
+    "ترسشان": [{ORTH: "ترس", NORM: "ترس"}, {ORTH: "شان", NORM: "شان"}],
+    "ترکش": [{ORTH: "ترک", NORM: "ترک"}, {ORTH: "ش", NORM: "ش"}],
+    "تشنه‌ت": [{ORTH: "تشنه‌", NORM: "تشنه‌"}, {ORTH: "ت", NORM: "ت"}],
+    "تشکیلاتی‌اش": [{ORTH: "تشکیلاتی‌", NORM: "تشکیلاتی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "تعلقش": [{ORTH: "تعلق", NORM: "تعلق"}, {ORTH: "ش", NORM: "ش"}],
+    "تلاششان": [{ORTH: "تلاش", NORM: "تلاش"}, {ORTH: "شان", NORM: "شان"}],
+    "تلاشمان": [{ORTH: "تلاش", NORM: "تلاش"}, {ORTH: "مان", NORM: "مان"}],
+    "تماشاگرش": [{ORTH: "تماشاگر", NORM: "تماشاگر"}, {ORTH: "ش", NORM: "ش"}],
+    "تمامشان": [{ORTH: "تمام", NORM: "تمام"}, {ORTH: "شان", NORM: "شان"}],
+    "تنش": [{ORTH: "تن", NORM: "تن"}, {ORTH: "ش", NORM: "ش"}],
+    "تنمان": [{ORTH: "تن", NORM: "تن"}, {ORTH: "مان", NORM: "مان"}],
+    "تنهایی‌اش": [{ORTH: "تنهایی‌", NORM: "تنهایی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "توانایی‌اش": [{ORTH: "توانایی‌", NORM: "توانایی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "توجهش": [{ORTH: "توجه", NORM: "توجه"}, {ORTH: "ش", NORM: "ش"}],
+    "توست": [{ORTH: "تو", NORM: "تو"}, {ORTH: "ست", NORM: "ست"}],
+    "توصیه‌اش": [{ORTH: "توصیه‌", NORM: "توصیه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "تیغه‌اش": [{ORTH: "تیغه‌", NORM: "تیغه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "جاست": [{ORTH: "جا", NORM: "جا"}, {ORTH: "ست", NORM: "ست"}],
+    "جامعه‌اند": [{ORTH: "جامعه‌", NORM: "جامعه‌"}, {ORTH: "اند", NORM: "اند"}],
+    "جانم": [{ORTH: "جان", NORM: "جان"}, {ORTH: "م", NORM: "م"}],
+    "جایش": [{ORTH: "جای", NORM: "جای"}, {ORTH: "ش", NORM: "ش"}],
+    "جایشان": [{ORTH: "جای", NORM: "جای"}, {ORTH: "شان", NORM: "شان"}],
+    "جدیدش": [{ORTH: "جدید", NORM: "جدید"}, {ORTH: "ش", NORM: "ش"}],
+    "جرمزاست": [{ORTH: "جرمزا", NORM: "جرمزا"}, {ORTH: "ست", NORM: "ست"}],
+    "جلوست": [{ORTH: "جلو", NORM: "جلو"}, {ORTH: "ست", NORM: "ست"}],
+    "جلویش": [{ORTH: "جلوی", NORM: "جلوی"}, {ORTH: "ش", NORM: "ش"}],
+    "جمهوریست": [{ORTH: "جمهوری", NORM: "جمهوری"}, {ORTH: "ست", NORM: "ست"}],
+    "جنسش": [{ORTH: "جنس", NORM: "جنس"}, {ORTH: "ش", NORM: "ش"}],
+    "جنس‌اند": [{ORTH: "جنس‌", NORM: "جنس‌"}, {ORTH: "اند", NORM: "اند"}],
+    "جوانانش": [{ORTH: "جوانان", NORM: "جوانان"}, {ORTH: "ش", NORM: "ش"}],
+    "جویش": [{ORTH: "جوی", NORM: "جوی"}, {ORTH: "ش", NORM: "ش"}],
+    "جگرش": [{ORTH: "جگر", NORM: "جگر"}, {ORTH: "ش", NORM: "ش"}],
+    "حاضرم": [{ORTH: "حاضر", NORM: "حاضر"}, {ORTH: "م", NORM: "م"}],
+    "حالتهایشان": [{ORTH: "حالتهای", NORM: "حالتهای"}, {ORTH: "شان", NORM: "شان"}],
+    "حالیست": [{ORTH: "حالی", NORM: "حالی"}, {ORTH: "ست", NORM: "ست"}],
+    "حالی‌مان": [{ORTH: "حالی‌", NORM: "حالی‌"}, {ORTH: "مان", NORM: "مان"}],
+    "حاکیست": [{ORTH: "حاکی", NORM: "حاکی"}, {ORTH: "ست", NORM: "ست"}],
+    "حرامزادگی‌اش": [
+        {ORTH: "حرامزادگی‌", NORM: "حرامزادگی‌"},
+        {ORTH: "اش", NORM: "اش"},
+    ],
+    "حرفتان": [{ORTH: "حرف", NORM: "حرف"}, {ORTH: "تان", NORM: "تان"}],
+    "حرفش": [{ORTH: "حرف", NORM: "حرف"}, {ORTH: "ش", NORM: "ش"}],
+    "حرفشان": [{ORTH: "حرف", NORM: "حرف"}, {ORTH: "شان", NORM: "شان"}],
+    "حرفم": [{ORTH: "حرف", NORM: "حرف"}, {ORTH: "م", NORM: "م"}],
+    "حرف‌های‌شان": [{ORTH: "حرف‌های‌", NORM: "حرف‌های‌"}, {ORTH: "شان", NORM: "شان"}],
+    "حرکتمان": [{ORTH: "حرکت", NORM: "حرکت"}, {ORTH: "مان", NORM: "مان"}],
+    "حریفانشان": [{ORTH: "حریفان", NORM: "حریفان"}, {ORTH: "شان", NORM: "شان"}],
+    "حضورشان": [{ORTH: "حضور", NORM: "حضور"}, {ORTH: "شان", NORM: "شان"}],
+    "حمایتش": [{ORTH: "حمایت", NORM: "حمایت"}, {ORTH: "ش", NORM: "ش"}],
+    "حواسش": [{ORTH: "حواس", NORM: "حواس"}, {ORTH: "ش", NORM: "ش"}],
+    "حواسشان": [{ORTH: "حواس", NORM: "حواس"}, {ORTH: "شان", NORM: "شان"}],
+    "حوصله‌مان": [{ORTH: "حوصله‌", NORM: "حوصله‌"}, {ORTH: "مان", NORM: "مان"}],
+    "حکومتش": [{ORTH: "حکومت", NORM: "حکومت"}, {ORTH: "ش", NORM: "ش"}],
+    "حکومتشان": [{ORTH: "حکومت", NORM: "حکومت"}, {ORTH: "شان", NORM: "شان"}],
+    "حیفم": [{ORTH: "حیف", NORM: "حیف"}, {ORTH: "م", NORM: "م"}],
+    "خاندانش": [{ORTH: "خاندان", NORM: "خاندان"}, {ORTH: "ش", NORM: "ش"}],
+    "خانه‌اش": [{ORTH: "خانه‌", NORM: "خانه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "خانه‌شان": [{ORTH: "خانه‌", NORM: "خانه‌"}, {ORTH: "شان", NORM: "شان"}],
+    "خانه‌مان": [{ORTH: "خانه‌", NORM: "خانه‌"}, {ORTH: "مان", NORM: "مان"}],
+    "خانه‌هایشان": [{ORTH: "خانه‌های", NORM: "خانه‌های"}, {ORTH: "شان", NORM: "شان"}],
+    "خانواده‌ات": [{ORTH: "خانواده", NORM: "خانواده"}, {ORTH: "‌ات", NORM: "ات"}],
+    "خانواده‌اش": [{ORTH: "خانواده‌", NORM: "خانواده‌"}, {ORTH: "اش", NORM: "اش"}],
+    "خانواده‌ام": [{ORTH: "خانواده‌", NORM: "خانواده‌"}, {ORTH: "ام", NORM: "ام"}],
+    "خانواده‌شان": [{ORTH: "خانواده‌", NORM: "خانواده‌"}, {ORTH: "شان", NORM: "شان"}],
+    "خداست": [{ORTH: "خدا", NORM: "خدا"}, {ORTH: "ست", NORM: "ست"}],
+    "خدایش": [{ORTH: "خدا", NORM: "خدا"}, {ORTH: "یش", NORM: "یش"}],
+    "خدایشان": [{ORTH: "خدای", NORM: "خدای"}, {ORTH: "شان", NORM: "شان"}],
+    "خردسالش": [{ORTH: "خردسال", NORM: "خردسال"}, {ORTH: "ش", NORM: "ش"}],
+    "خروپفشان": [{ORTH: "خروپف", NORM: "خروپف"}, {ORTH: "شان", NORM: "شان"}],
+    "خسته‌ای": [{ORTH: "خسته‌", NORM: "خسته‌"}, {ORTH: "ای", NORM: "ای"}],
+    "خطت": [{ORTH: "خط", NORM: "خط"}, {ORTH: "ت", NORM: "ت"}],
+    "خوابمان": [{ORTH: "خواب", NORM: "خواب"}, {ORTH: "مان", NORM: "مان"}],
+    "خواندنش": [{ORTH: "خواندن", NORM: "خواندن"}, {ORTH: "ش", NORM: "ش"}],
+    "خواهرش": [{ORTH: "خواهر", NORM: "خواهر"}, {ORTH: "ش", NORM: "ش"}],
+    "خوبش": [{ORTH: "خوب", NORM: "خوب"}, {ORTH: "ش", NORM: "ش"}],
+    "خودت": [{ORTH: "خود", NORM: "خود"}, {ORTH: "ت", NORM: "ت"}],
+    "خودتان": [{ORTH: "خود", NORM: "خود"}, {ORTH: "تان", NORM: "تان"}],
+    "خودش": [{ORTH: "خود", NORM: "خود"}, {ORTH: "ش", NORM: "ش"}],
+    "خودشان": [{ORTH: "خود", NORM: "خود"}, {ORTH: "شان", NORM: "شان"}],
+    "خودمان": [{ORTH: "خود", NORM: "خود"}, {ORTH: "مان", NORM: "مان"}],
+    "خوردمان": [{ORTH: "خورد", NORM: "خورد"}, {ORTH: "مان", NORM: "مان"}],
+    "خوردنشان": [{ORTH: "خوردن", NORM: "خوردن"}, {ORTH: "شان", NORM: "شان"}],
+    "خوشش": [{ORTH: "خوش", NORM: "خوش"}, {ORTH: "ش", NORM: "ش"}],
+    "خوشوقتم": [{ORTH: "خوشوقت", NORM: "خوشوقت"}, {ORTH: "م", NORM: "م"}],
+    "خونشان": [{ORTH: "خون", NORM: "خون"}, {ORTH: "شان", NORM: "شان"}],
+    "خویش": [{ORTH: "خوی", NORM: "خوی"}, {ORTH: "ش", NORM: "ش"}],
+    "خویشتنم": [{ORTH: "خویشتن", NORM: "خویشتن"}, {ORTH: "م", NORM: "م"}],
+    "خیالش": [{ORTH: "خیال", NORM: "خیال"}, {ORTH: "ش", NORM: "ش"}],
+    "خیسش": [{ORTH: "خیس", NORM: "خیس"}, {ORTH: "ش", NORM: "ش"}],
+    "داراست": [{ORTH: "دارا", NORM: "دارا"}, {ORTH: "ست", NORM: "ست"}],
+    "داستانهایش": [{ORTH: "داستانهای", NORM: "داستانهای"}, {ORTH: "ش", NORM: "ش"}],
+    "دخترمان": [{ORTH: "دختر", NORM: "دختر"}, {ORTH: "مان", NORM: "مان"}],
+    "دخیلند": [{ORTH: "دخیل", NORM: "دخیل"}, {ORTH: "ند", NORM: "ند"}],
+    "درباره‌ات": [{ORTH: "درباره", NORM: "درباره"}, {ORTH: "‌ات", NORM: "ات"}],
+    "درباره‌اش": [{ORTH: "درباره‌", NORM: "درباره‌"}, {ORTH: "اش", NORM: "اش"}],
+    "دردش": [{ORTH: "درد", NORM: "درد"}, {ORTH: "ش", NORM: "ش"}],
+    "دردشان": [{ORTH: "درد", NORM: "درد"}, {ORTH: "شان", NORM: "شان"}],
+    "درسته": [{ORTH: "درست", NORM: "درست"}, {ORTH: "ه", NORM: "ه"}],
+    "درش": [{ORTH: "در", NORM: "در"}, {ORTH: "ش", NORM: "ش"}],
+    "درون‌شان": [{ORTH: "درون‌", NORM: "درون‌"}, {ORTH: "شان", NORM: "شان"}],
+    "درین": [{ORTH: "در", NORM: "در"}, {ORTH: "ین", NORM: "ین"}],
+    "دریچه‌هایش": [{ORTH: "دریچه‌های", NORM: "دریچه‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "دزدانش": [{ORTH: "دزدان", NORM: "دزدان"}, {ORTH: "ش", NORM: "ش"}],
+    "دستت": [{ORTH: "دست", NORM: "دست"}, {ORTH: "ت", NORM: "ت"}],
+    "دستش": [{ORTH: "دست", NORM: "دست"}, {ORTH: "ش", NORM: "ش"}],
+    "دستمان": [{ORTH: "دست", NORM: "دست"}, {ORTH: "مان", NORM: "مان"}],
+    "دستهایشان": [{ORTH: "دستهای", NORM: "دستهای"}, {ORTH: "شان", NORM: "شان"}],
+    "دست‌یافتنی‌ست": [
+        {ORTH: "دست‌یافتنی‌", NORM: "دست‌یافتنی‌"},
+        {ORTH: "ست", NORM: "ست"},
+    ],
+    "دشمنند": [{ORTH: "دشمن", NORM: "دشمن"}, {ORTH: "ند", NORM: "ند"}],
+    "دشمنیشان": [{ORTH: "دشمنی", NORM: "دشمنی"}, {ORTH: "شان", NORM: "شان"}],
+    "دشمنیم": [{ORTH: "دشمن", NORM: "دشمن"}, {ORTH: "یم", NORM: "یم"}],
+    "دفترش": [{ORTH: "دفتر", NORM: "دفتر"}, {ORTH: "ش", NORM: "ش"}],
+    "دفنشان": [{ORTH: "دفن", NORM: "دفن"}, {ORTH: "شان", NORM: "شان"}],
+    "دلت": [{ORTH: "دل", NORM: "دل"}, {ORTH: "ت", NORM: "ت"}],
+    "دلش": [{ORTH: "دل", NORM: "دل"}, {ORTH: "ش", NORM: "ش"}],
+    "دلشان": [{ORTH: "دل", NORM: "دل"}, {ORTH: "شان", NORM: "شان"}],
+    "دلم": [{ORTH: "دل", NORM: "دل"}, {ORTH: "م", NORM: "م"}],
+    "دلیلش": [{ORTH: "دلیل", NORM: "دلیل"}, {ORTH: "ش", NORM: "ش"}],
+    "دنبالش": [{ORTH: "دنبال", NORM: "دنبال"}, {ORTH: "ش", NORM: "ش"}],
+    "دنباله‌اش": [{ORTH: "دنباله‌", NORM: "دنباله‌"}, {ORTH: "اش", NORM: "اش"}],
+    "دهاتی‌هایش": [{ORTH: "دهاتی‌های", NORM: "دهاتی‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "دهانت": [{ORTH: "دهان", NORM: "دهان"}, {ORTH: "ت", NORM: "ت"}],
+    "دهنش": [{ORTH: "دهن", NORM: "دهن"}, {ORTH: "ش", NORM: "ش"}],
+    "دورش": [{ORTH: "دور", NORM: "دور"}, {ORTH: "ش", NORM: "ش"}],
+    "دوروبریهاشان": [
+        {ORTH: "دوروبریها", NORM: "دوروبریها"},
+        {ORTH: "شان", NORM: "شان"},
+    ],
+    "دوستانش": [{ORTH: "دوستان", NORM: "دوستان"}, {ORTH: "ش", NORM: "ش"}],
+    "دوستانشان": [{ORTH: "دوستان", NORM: "دوستان"}, {ORTH: "شان", NORM: "شان"}],
+    "دوستت": [{ORTH: "دوست", NORM: "دوست"}, {ORTH: "ت", NORM: "ت"}],
+    "دوستش": [{ORTH: "دوست", NORM: "دوست"}, {ORTH: "ش", NORM: "ش"}],
+    "دومش": [{ORTH: "دوم", NORM: "دوم"}, {ORTH: "ش", NORM: "ش"}],
+    "دویدنش": [{ORTH: "دویدن", NORM: "دویدن"}, {ORTH: "ش", NORM: "ش"}],
+    "دکورهایمان": [{ORTH: "دکورهای", NORM: "دکورهای"}, {ORTH: "مان", NORM: "مان"}],
+    "دیدگاهش": [{ORTH: "دیدگاه", NORM: "دیدگاه"}, {ORTH: "ش", NORM: "ش"}],
+    "دیرت": [{ORTH: "دیر", NORM: "دیر"}, {ORTH: "ت", NORM: "ت"}],
+    "دیرم": [{ORTH: "دیر", NORM: "دیر"}, {ORTH: "م", NORM: "م"}],
+    "دینت": [{ORTH: "دین", NORM: "دین"}, {ORTH: "ت", NORM: "ت"}],
+    "دینش": [{ORTH: "دین", NORM: "دین"}, {ORTH: "ش", NORM: "ش"}],
+    "دین‌شان": [{ORTH: "دین‌", NORM: "دین‌"}, {ORTH: "شان", NORM: "شان"}],
+    "دیواره‌هایش": [{ORTH: "دیواره‌های", NORM: "دیواره‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "دیوانه‌ای": [{ORTH: "دیوانه‌", NORM: "دیوانه‌"}, {ORTH: "ای", NORM: "ای"}],
+    "دیوی": [{ORTH: "دیو", NORM: "دیو"}, {ORTH: "ی", NORM: "ی"}],
+    "دیگرم": [{ORTH: "دیگر", NORM: "دیگر"}, {ORTH: "م", NORM: "م"}],
+    "دیگرمان": [{ORTH: "دیگر", NORM: "دیگر"}, {ORTH: "مان", NORM: "مان"}],
+    "ذهنش": [{ORTH: "ذهن", NORM: "ذهن"}, {ORTH: "ش", NORM: "ش"}],
+    "ذهنشان": [{ORTH: "ذهن", NORM: "ذهن"}, {ORTH: "شان", NORM: "شان"}],
+    "ذهنم": [{ORTH: "ذهن", NORM: "ذهن"}, {ORTH: "م", NORM: "م"}],
+    "رئوسش": [{ORTH: "رئوس", NORM: "رئوس"}, {ORTH: "ش", NORM: "ش"}],
+    "راهشان": [{ORTH: "راه", NORM: "راه"}, {ORTH: "شان", NORM: "شان"}],
+    "راهگشاست": [{ORTH: "راهگشا", NORM: "راهگشا"}, {ORTH: "ست", NORM: "ست"}],
+    "رایانه‌هایشان": [
+        {ORTH: "رایانه‌های", NORM: "رایانه‌های"},
+        {ORTH: "شان", NORM: "شان"},
+    ],
+    "رعایتشان": [{ORTH: "رعایت", NORM: "رعایت"}, {ORTH: "شان", NORM: "شان"}],
+    "رفتارش": [{ORTH: "رفتار", NORM: "رفتار"}, {ORTH: "ش", NORM: "ش"}],
+    "رفتارشان": [{ORTH: "رفتار", NORM: "رفتار"}, {ORTH: "شان", NORM: "شان"}],
+    "رفتارمان": [{ORTH: "رفتار", NORM: "رفتار"}, {ORTH: "مان", NORM: "مان"}],
+    "رفتارهاست": [{ORTH: "رفتارها", NORM: "رفتارها"}, {ORTH: "ست", NORM: "ست"}],
+    "رفتارهایشان": [{ORTH: "رفتارهای", NORM: "رفتارهای"}, {ORTH: "شان", NORM: "شان"}],
+    "رفقایم": [{ORTH: "رفقا", NORM: "رفقا"}, {ORTH: "یم", NORM: "یم"}],
+    "رقیق‌ترش": [{ORTH: "رقیق‌تر", NORM: "رقیق‌تر"}, {ORTH: "ش", NORM: "ش"}],
+    "رنجند": [{ORTH: "رنج", NORM: "رنج"}, {ORTH: "ند", NORM: "ند"}],
+    "رهگشاست": [{ORTH: "رهگشا", NORM: "رهگشا"}, {ORTH: "ست", NORM: "ست"}],
+    "رواست": [{ORTH: "روا", NORM: "روا"}, {ORTH: "ست", NORM: "ست"}],
+    "روبروست": [{ORTH: "روبرو", NORM: "روبرو"}, {ORTH: "ست", NORM: "ست"}],
+    "روحی‌اش": [{ORTH: "روحی‌", NORM: "روحی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "روزنامه‌اش": [{ORTH: "روزنامه‌", NORM: "روزنامه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "روزه‌ست": [{ORTH: "روزه‌", NORM: "روزه‌"}, {ORTH: "ست", NORM: "ست"}],
+    "روسری‌اش": [{ORTH: "روسری‌", NORM: "روسری‌"}, {ORTH: "اش", NORM: "اش"}],
+    "روشتان": [{ORTH: "روش", NORM: "روش"}, {ORTH: "تان", NORM: "تان"}],
+    "رویش": [{ORTH: "روی", NORM: "روی"}, {ORTH: "ش", NORM: "ش"}],
+    "زبانش": [{ORTH: "زبان", NORM: "زبان"}, {ORTH: "ش", NORM: "ش"}],
+    "زحماتشان": [{ORTH: "زحمات", NORM: "زحمات"}, {ORTH: "شان", NORM: "شان"}],
+    "زدنهایشان": [{ORTH: "زدنهای", NORM: "زدنهای"}, {ORTH: "شان", NORM: "شان"}],
+    "زرنگشان": [{ORTH: "زرنگ", NORM: "زرنگ"}, {ORTH: "شان", NORM: "شان"}],
+    "زشتش": [{ORTH: "زشت", NORM: "زشت"}, {ORTH: "ش", NORM: "ش"}],
+    "زشتکارانند": [{ORTH: "زشتکاران", NORM: "زشتکاران"}, {ORTH: "ند", NORM: "ند"}],
+    "زلفش": [{ORTH: "زلف", NORM: "زلف"}, {ORTH: "ش", NORM: "ش"}],
+    "زمن": [{ORTH: "ز", NORM: "ز"}, {ORTH: "من", NORM: "من"}],
+    "زنبوری‌اش": [{ORTH: "زنبوری‌", NORM: "زنبوری‌"}, {ORTH: "اش", NORM: "اش"}],
+    "زندانم": [{ORTH: "زندان", NORM: "زندان"}, {ORTH: "م", NORM: "م"}],
+    "زنده‌ام": [{ORTH: "زنده‌", NORM: "زنده‌"}, {ORTH: "ام", NORM: "ام"}],
+    "زندگانی‌اش": [{ORTH: "زندگانی‌", NORM: "زندگانی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "زندگی‌اش": [{ORTH: "زندگی‌", NORM: "زندگی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "زندگی‌ام": [{ORTH: "زندگی‌", NORM: "زندگی‌"}, {ORTH: "ام", NORM: "ام"}],
+    "زندگی‌شان": [{ORTH: "زندگی‌", NORM: "زندگی‌"}, {ORTH: "شان", NORM: "شان"}],
+    "زنش": [{ORTH: "زن", NORM: "زن"}, {ORTH: "ش", NORM: "ش"}],
+    "زنند": [{ORTH: "زن", NORM: "زن"}, {ORTH: "ند", NORM: "ند"}],
+    "زو": [{ORTH: "ز", NORM: "ز"}, {ORTH: "و", NORM: "و"}],
+    "زیاده": [{ORTH: "زیاد", NORM: "زیاد"}, {ORTH: "ه", NORM: "ه"}],
+    "زیباست": [{ORTH: "زیبا", NORM: "زیبا"}, {ORTH: "ست", NORM: "ست"}],
+    "زیبایش": [{ORTH: "زیبای", NORM: "زیبای"}, {ORTH: "ش", NORM: "ش"}],
+    "زیبایی": [{ORTH: "زیبای", NORM: "زیبای"}, {ORTH: "ی", NORM: "ی"}],
+    "زیربناست": [{ORTH: "زیربنا", NORM: "زیربنا"}, {ORTH: "ست", NORM: "ست"}],
+    "زیرک‌اند": [{ORTH: "زیرک‌", NORM: "زیرک‌"}, {ORTH: "اند", NORM: "اند"}],
+    "سؤالتان": [{ORTH: "سؤال", NORM: "سؤال"}, {ORTH: "تان", NORM: "تان"}],
+    "سؤالم": [{ORTH: "سؤال", NORM: "سؤال"}, {ORTH: "م", NORM: "م"}],
+    "سابقه‌اش": [{ORTH: "سابقه‌", NORM: "سابقه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "ساختنم": [{ORTH: "ساختن", NORM: "ساختن"}, {ORTH: "م", NORM: "م"}],
+    "ساده‌اش": [{ORTH: "ساده‌", NORM: "ساده‌"}, {ORTH: "اش", NORM: "اش"}],
+    "ساده‌اند": [{ORTH: "ساده‌", NORM: "ساده‌"}, {ORTH: "اند", NORM: "اند"}],
+    "سازمانش": [{ORTH: "سازمان", NORM: "سازمان"}, {ORTH: "ش", NORM: "ش"}],
+    "ساعتم": [{ORTH: "ساعت", NORM: "ساعت"}, {ORTH: "م", NORM: "م"}],
+    "سالته": [
+        {ORTH: "سال", NORM: "سال"},
+        {ORTH: "ت", NORM: "ت"},
+        {ORTH: "ه", NORM: "ه"},
+    ],
+    "سالش": [{ORTH: "سال", NORM: "سال"}, {ORTH: "ش", NORM: "ش"}],
+    "سالهاست": [{ORTH: "سالها", NORM: "سالها"}, {ORTH: "ست", NORM: "ست"}],
+    "ساله‌اش": [{ORTH: "ساله‌", NORM: "ساله‌"}, {ORTH: "اش", NORM: "اش"}],
+    "ساکتند": [{ORTH: "ساکت", NORM: "ساکت"}, {ORTH: "ند", NORM: "ند"}],
+    "ساکنند": [{ORTH: "ساکن", NORM: "ساکن"}, {ORTH: "ند", NORM: "ند"}],
+    "سبزشان": [{ORTH: "سبز", NORM: "سبز"}, {ORTH: "شان", NORM: "شان"}],
+    "سبیل‌مان": [{ORTH: "سبیل‌", NORM: "سبیل‌"}, {ORTH: "مان", NORM: "مان"}],
+    "ستم‌هایش": [{ORTH: "ستم‌های", NORM: "ستم‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "سخنانش": [{ORTH: "سخنان", NORM: "سخنان"}, {ORTH: "ش", NORM: "ش"}],
+    "سخنانشان": [{ORTH: "سخنان", NORM: "سخنان"}, {ORTH: "شان", NORM: "شان"}],
+    "سخنتان": [{ORTH: "سخن", NORM: "سخن"}, {ORTH: "تان", NORM: "تان"}],
+    "سخنش": [{ORTH: "سخن", NORM: "سخن"}, {ORTH: "ش", NORM: "ش"}],
+    "سخنم": [{ORTH: "سخن", NORM: "سخن"}, {ORTH: "م", NORM: "م"}],
+    "سردش": [{ORTH: "سرد", NORM: "سرد"}, {ORTH: "ش", NORM: "ش"}],
+    "سرزمینشان": [{ORTH: "سرزمین", NORM: "سرزمین"}, {ORTH: "شان", NORM: "شان"}],
+    "سرش": [{ORTH: "سر", NORM: "سر"}, {ORTH: "ش", NORM: "ش"}],
+    "سرمایه‌دارهاست": [
+        {ORTH: "سرمایه‌دارها", NORM: "سرمایه‌دارها"},
+        {ORTH: "ست", NORM: "ست"},
+    ],
+    "سرنوشتش": [{ORTH: "سرنوشت", NORM: "سرنوشت"}, {ORTH: "ش", NORM: "ش"}],
+    "سرنوشتشان": [{ORTH: "سرنوشت", NORM: "سرنوشت"}, {ORTH: "شان", NORM: "شان"}],
+    "سروتهش": [{ORTH: "سروته", NORM: "سروته"}, {ORTH: "ش", NORM: "ش"}],
+    "سرچشمه‌اش": [{ORTH: "سرچشمه‌", NORM: "سرچشمه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "سقمش": [{ORTH: "سقم", NORM: "سقم"}, {ORTH: "ش", NORM: "ش"}],
+    "سنش": [{ORTH: "سن", NORM: "سن"}, {ORTH: "ش", NORM: "ش"}],
+    "سپاهش": [{ORTH: "سپاه", NORM: "سپاه"}, {ORTH: "ش", NORM: "ش"}],
+    "سیاسیشان": [{ORTH: "سیاسی", NORM: "سیاسی"}, {ORTH: "شان", NORM: "شان"}],
+    "سیاه‌چاله‌هاست": [
+        {ORTH: "سیاه‌چاله‌ها", NORM: "سیاه‌چاله‌ها"},
+        {ORTH: "ست", NORM: "ست"},
+    ],
+    "شاخه‌هایشان": [{ORTH: "شاخه‌های", NORM: "شاخه‌های"}, {ORTH: "شان", NORM: "شان"}],
+    "شالوده‌اش": [{ORTH: "شالوده‌", NORM: "شالوده‌"}, {ORTH: "اش", NORM: "اش"}],
+    "شانه‌هایش": [{ORTH: "شانه‌های", NORM: "شانه‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "شاهدیم": [{ORTH: "شاهد", NORM: "شاهد"}, {ORTH: "یم", NORM: "یم"}],
+    "شاهکارهایش": [{ORTH: "شاهکارهای", NORM: "شاهکارهای"}, {ORTH: "ش", NORM: "ش"}],
+    "شخصیتش": [{ORTH: "شخصیت", NORM: "شخصیت"}, {ORTH: "ش", NORM: "ش"}],
+    "شدنشان": [{ORTH: "شدن", NORM: "شدن"}, {ORTH: "شان", NORM: "شان"}],
+    "شرکتیست": [{ORTH: "شرکتی", NORM: "شرکتی"}, {ORTH: "ست", NORM: "ست"}],
+    "شعارهاشان": [{ORTH: "شعارها", NORM: "شعارها"}, {ORTH: "شان", NORM: "شان"}],
+    "شعورش": [{ORTH: "شعور", NORM: "شعور"}, {ORTH: "ش", NORM: "ش"}],
+    "شغلش": [{ORTH: "شغل", NORM: "شغل"}, {ORTH: "ش", NORM: "ش"}],
+    "شماست": [{ORTH: "شما", NORM: "شما"}, {ORTH: "ست", NORM: "ست"}],
+    "شمشیرش": [{ORTH: "شمشیر", NORM: "شمشیر"}, {ORTH: "ش", NORM: "ش"}],
+    "شنیدنش": [{ORTH: "شنیدن", NORM: "شنیدن"}, {ORTH: "ش", NORM: "ش"}],
+    "شوراست": [{ORTH: "شورا", NORM: "شورا"}, {ORTH: "ست", NORM: "ست"}],
+    "شومت": [{ORTH: "شوم", NORM: "شوم"}, {ORTH: "ت", NORM: "ت"}],
+    "شیرینترش": [{ORTH: "شیرینتر", NORM: "شیرینتر"}, {ORTH: "ش", NORM: "ش"}],
+    "شیطان‌اند": [{ORTH: "شیطان‌", NORM: "شیطان‌"}, {ORTH: "اند", NORM: "اند"}],
+    "شیوه‌هاست": [{ORTH: "شیوه‌ها", NORM: "شیوه‌ها"}, {ORTH: "ست", NORM: "ست"}],
+    "صاحبش": [{ORTH: "صاحب", NORM: "صاحب"}, {ORTH: "ش", NORM: "ش"}],
+    "صحنه‌اش": [{ORTH: "صحنه‌", NORM: "صحنه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "صدایش": [{ORTH: "صدای", NORM: "صدای"}, {ORTH: "ش", NORM: "ش"}],
+    "صددند": [{ORTH: "صدد", NORM: "صدد"}, {ORTH: "ند", NORM: "ند"}],
+    "صندوق‌هاست": [{ORTH: "صندوق‌ها", NORM: "صندوق‌ها"}, {ORTH: "ست", NORM: "ست"}],
+    "صندوق‌هایش": [{ORTH: "صندوق‌های", NORM: "صندوق‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "صورتش": [{ORTH: "صورت", NORM: "صورت"}, {ORTH: "ش", NORM: "ش"}],
+    "ضروری‌اند": [{ORTH: "ضروری‌", NORM: "ضروری‌"}, {ORTH: "اند", NORM: "اند"}],
+    "ضمیرش": [{ORTH: "ضمیر", NORM: "ضمیر"}, {ORTH: "ش", NORM: "ش"}],
+    "طرفش": [{ORTH: "طرف", NORM: "طرف"}, {ORTH: "ش", NORM: "ش"}],
+    "طلسمش": [{ORTH: "طلسم", NORM: "طلسم"}, {ORTH: "ش", NORM: "ش"}],
+    "طوره": [{ORTH: "طور", NORM: "طور"}, {ORTH: "ه", NORM: "ه"}],
+    "عاشوراست": [{ORTH: "عاشورا", NORM: "عاشورا"}, {ORTH: "ست", NORM: "ست"}],
+    "عبارتند": [{ORTH: "عبارت", NORM: "عبارت"}, {ORTH: "ند", NORM: "ند"}],
+    "عزیزانتان": [{ORTH: "عزیزان", NORM: "عزیزان"}, {ORTH: "تان", NORM: "تان"}],
+    "عزیزانش": [{ORTH: "عزیزان", NORM: "عزیزان"}, {ORTH: "ش", NORM: "ش"}],
+    "عزیزش": [{ORTH: "عزیز", NORM: "عزیز"}, {ORTH: "ش", NORM: "ش"}],
+    "عشرت‌طلبی‌اش": [
+        {ORTH: "عشرت‌طلبی‌", NORM: "عشرت‌طلبی‌"},
+        {ORTH: "اش", NORM: "اش"},
+    ],
+    "عقبیم": [{ORTH: "عقب", NORM: "عقب"}, {ORTH: "یم", NORM: "یم"}],
+    "علاقه‌اش": [{ORTH: "علاقه‌", NORM: "علاقه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "علمیمان": [{ORTH: "علمی", NORM: "علمی"}, {ORTH: "مان", NORM: "مان"}],
+    "عمرش": [{ORTH: "عمر", NORM: "عمر"}, {ORTH: "ش", NORM: "ش"}],
+    "عمرشان": [{ORTH: "عمر", NORM: "عمر"}, {ORTH: "شان", NORM: "شان"}],
+    "عملش": [{ORTH: "عمل", NORM: "عمل"}, {ORTH: "ش", NORM: "ش"}],
+    "عملی‌اند": [{ORTH: "عملی‌", NORM: "عملی‌"}, {ORTH: "اند", NORM: "اند"}],
+    "عمویت": [{ORTH: "عموی", NORM: "عموی"}, {ORTH: "ت", NORM: "ت"}],
+    "عمویش": [{ORTH: "عموی", NORM: "عموی"}, {ORTH: "ش", NORM: "ش"}],
+    "عمیقش": [{ORTH: "عمیق", NORM: "عمیق"}, {ORTH: "ش", NORM: "ش"}],
+    "عواملش": [{ORTH: "عوامل", NORM: "عوامل"}, {ORTH: "ش", NORM: "ش"}],
+    "عوضشان": [{ORTH: "عوض", NORM: "عوض"}, {ORTH: "شان", NORM: "شان"}],
+    "غذایی‌شان": [{ORTH: "غذایی‌", NORM: "غذایی‌"}, {ORTH: "شان", NORM: "شان"}],
+    "غریبه‌اند": [{ORTH: "غریبه‌", NORM: "غریبه‌"}, {ORTH: "اند", NORM: "اند"}],
+    "غلامانش": [{ORTH: "غلامان", NORM: "غلامان"}, {ORTH: "ش", NORM: "ش"}],
+    "غلطهاست": [{ORTH: "غلطها", NORM: "غلطها"}, {ORTH: "ست", NORM: "ست"}],
+    "فراموشتان": [{ORTH: "فراموش", NORM: "فراموش"}, {ORTH: "تان", NORM: "تان"}],
+    "فردی‌اند": [{ORTH: "فردی‌", NORM: "فردی‌"}, {ORTH: "اند", NORM: "اند"}],
+    "فرزندانش": [{ORTH: "فرزندان", NORM: "فرزندان"}, {ORTH: "ش", NORM: "ش"}],
+    "فرزندش": [{ORTH: "فرزند", NORM: "فرزند"}, {ORTH: "ش", NORM: "ش"}],
+    "فرم‌هایش": [{ORTH: "فرم‌های", NORM: "فرم‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "فرهنگی‌مان": [{ORTH: "فرهنگی‌", NORM: "فرهنگی‌"}, {ORTH: "مان", NORM: "مان"}],
+    "فریادشان": [{ORTH: "فریاد", NORM: "فریاد"}, {ORTH: "شان", NORM: "شان"}],
+    "فضایی‌شان": [{ORTH: "فضایی‌", NORM: "فضایی‌"}, {ORTH: "شان", NORM: "شان"}],
+    "فقیرشان": [{ORTH: "فقیر", NORM: "فقیر"}, {ORTH: "شان", NORM: "شان"}],
+    "فوری‌شان": [{ORTH: "فوری‌", NORM: "فوری‌"}, {ORTH: "شان", NORM: "شان"}],
+    "قائلند": [{ORTH: "قائل", NORM: "قائل"}, {ORTH: "ند", NORM: "ند"}],
+    "قائلیم": [{ORTH: "قائل", NORM: "قائل"}, {ORTH: "یم", NORM: "یم"}],
+    "قادرند": [{ORTH: "قادر", NORM: "قادر"}, {ORTH: "ند", NORM: "ند"}],
+    "قانونمندش": [{ORTH: "قانونمند", NORM: "قانونمند"}, {ORTH: "ش", NORM: "ش"}],
+    "قبلند": [{ORTH: "قبل", NORM: "قبل"}, {ORTH: "ند", NORM: "ند"}],
+    "قبلی‌اش": [{ORTH: "قبلی‌", NORM: "قبلی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "قبلی‌مان": [{ORTH: "قبلی‌", NORM: "قبلی‌"}, {ORTH: "مان", NORM: "مان"}],
+    "قدریست": [{ORTH: "قدری", NORM: "قدری"}, {ORTH: "ست", NORM: "ست"}],
+    "قدمش": [{ORTH: "قدم", NORM: "قدم"}, {ORTH: "ش", NORM: "ش"}],
+    "قسمتش": [{ORTH: "قسمت", NORM: "قسمت"}, {ORTH: "ش", NORM: "ش"}],
+    "قضایاست": [{ORTH: "قضایا", NORM: "قضایا"}, {ORTH: "ست", NORM: "ست"}],
+    "قضیه‌شان": [{ORTH: "قضیه‌", NORM: "قضیه‌"}, {ORTH: "شان", NORM: "شان"}],
+    "قهرمانهایشان": [
+        {ORTH: "قهرمانهای", NORM: "قهرمانهای"},
+        {ORTH: "شان", NORM: "شان"},
+    ],
+    "قهرمانیش": [{ORTH: "قهرمانی", NORM: "قهرمانی"}, {ORTH: "ش", NORM: "ش"}],
+    "قومت": [{ORTH: "قوم", NORM: "قوم"}, {ORTH: "ت", NORM: "ت"}],
+    "لازمه‌اش": [{ORTH: "لازمه‌", NORM: "لازمه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "مأموریتش": [{ORTH: "مأموریت", NORM: "مأموریت"}, {ORTH: "ش", NORM: "ش"}],
+    "مأموریتم": [{ORTH: "مأموریت", NORM: "مأموریت"}, {ORTH: "م", NORM: "م"}],
+    "مأموریت‌اند": [{ORTH: "مأموریت‌", NORM: "مأموریت‌"}, {ORTH: "اند", NORM: "اند"}],
+    "مادرانشان": [{ORTH: "مادران", NORM: "مادران"}, {ORTH: "شان", NORM: "شان"}],
+    "مادرت": [{ORTH: "مادر", NORM: "مادر"}, {ORTH: "ت", NORM: "ت"}],
+    "مادرش": [{ORTH: "مادر", NORM: "مادر"}, {ORTH: "ش", NORM: "ش"}],
+    "مادرم": [{ORTH: "مادر", NORM: "مادر"}, {ORTH: "م", NORM: "م"}],
+    "ماست": [{ORTH: "ما", NORM: "ما"}, {ORTH: "ست", NORM: "ست"}],
+    "مالی‌اش": [{ORTH: "مالی‌", NORM: "مالی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "ماهیتش": [{ORTH: "ماهیت", NORM: "ماهیت"}, {ORTH: "ش", NORM: "ش"}],
+    "مایی": [{ORTH: "ما", NORM: "ما"}, {ORTH: "یی", NORM: "یی"}],
+    "مجازاتش": [{ORTH: "مجازات", NORM: "مجازات"}, {ORTH: "ش", NORM: "ش"}],
+    "مجبورند": [{ORTH: "مجبور", NORM: "مجبور"}, {ORTH: "ند", NORM: "ند"}],
+    "محتاجند": [{ORTH: "محتاج", NORM: "محتاج"}, {ORTH: "ند", NORM: "ند"}],
+    "محرمم": [{ORTH: "محرم", NORM: "محرم"}, {ORTH: "م", NORM: "م"}],
+    "محلش": [{ORTH: "محل", NORM: "محل"}, {ORTH: "ش", NORM: "ش"}],
+    "مخالفند": [{ORTH: "مخالف", NORM: "مخالف"}, {ORTH: "ند", NORM: "ند"}],
+    "مخدرش": [{ORTH: "مخدر", NORM: "مخدر"}, {ORTH: "ش", NORM: "ش"}],
+    "مدتهاست": [{ORTH: "مدتها", NORM: "مدتها"}, {ORTH: "ست", NORM: "ست"}],
+    "مدرسه‌ات": [{ORTH: "مدرسه", NORM: "مدرسه"}, {ORTH: "‌ات", NORM: "ات"}],
+    "مدرکم": [{ORTH: "مدرک", NORM: "مدرک"}, {ORTH: "م", NORM: "م"}],
+    "مدیرانش": [{ORTH: "مدیران", NORM: "مدیران"}, {ORTH: "ش", NORM: "ش"}],
+    "مدیونم": [{ORTH: "مدیون", NORM: "مدیون"}, {ORTH: "م", NORM: "م"}],
+    "مذهبی‌اند": [{ORTH: "مذهبی‌", NORM: "مذهبی‌"}, {ORTH: "اند", NORM: "اند"}],
+    "مرا": [{ORTH: "م", NORM: "م"}, {ORTH: "را", NORM: "را"}],
+    "مرادت": [{ORTH: "مراد", NORM: "مراد"}, {ORTH: "ت", NORM: "ت"}],
+    "مردمشان": [{ORTH: "مردم", NORM: "مردم"}, {ORTH: "شان", NORM: "شان"}],
+    "مردمند": [{ORTH: "مردم", NORM: "مردم"}, {ORTH: "ند", NORM: "ند"}],
+    "مردم‌اند": [{ORTH: "مردم‌", NORM: "مردم‌"}, {ORTH: "اند", NORM: "اند"}],
+    "مرزشان": [{ORTH: "مرز", NORM: "مرز"}, {ORTH: "شان", NORM: "شان"}],
+    "مرزهاشان": [{ORTH: "مرزها", NORM: "مرزها"}, {ORTH: "شان", NORM: "شان"}],
+    "مزدورش": [{ORTH: "مزدور", NORM: "مزدور"}, {ORTH: "ش", NORM: "ش"}],
+    "مسئولیتش": [{ORTH: "مسئولیت", NORM: "مسئولیت"}, {ORTH: "ش", NORM: "ش"}],
+    "مسائلش": [{ORTH: "مسائل", NORM: "مسائل"}, {ORTH: "ش", NORM: "ش"}],
+    "مستحضرید": [{ORTH: "مستحضر", NORM: "مستحضر"}, {ORTH: "ید", NORM: "ید"}],
+    "مسلمانم": [{ORTH: "مسلمان", NORM: "مسلمان"}, {ORTH: "م", NORM: "م"}],
+    "مسلمانند": [{ORTH: "مسلمان", NORM: "مسلمان"}, {ORTH: "ند", NORM: "ند"}],
+    "مشتریانش": [{ORTH: "مشتریان", NORM: "مشتریان"}, {ORTH: "ش", NORM: "ش"}],
+    "مشتهایمان": [{ORTH: "مشتهای", NORM: "مشتهای"}, {ORTH: "مان", NORM: "مان"}],
+    "مشخصند": [{ORTH: "مشخص", NORM: "مشخص"}, {ORTH: "ند", NORM: "ند"}],
+    "مشغولند": [{ORTH: "مشغول", NORM: "مشغول"}, {ORTH: "ند", NORM: "ند"}],
+    "مشغولیم": [{ORTH: "مشغول", NORM: "مشغول"}, {ORTH: "یم", NORM: "یم"}],
+    "مشهورش": [{ORTH: "مشهور", NORM: "مشهور"}, {ORTH: "ش", NORM: "ش"}],
+    "مشکلاتشان": [{ORTH: "مشکلات", NORM: "مشکلات"}, {ORTH: "شان", NORM: "شان"}],
+    "مشکلم": [{ORTH: "مشکل", NORM: "مشکل"}, {ORTH: "م", NORM: "م"}],
+    "مطمئنم": [{ORTH: "مطمئن", NORM: "مطمئن"}, {ORTH: "م", NORM: "م"}],
+    "معامله‌مان": [{ORTH: "معامله‌", NORM: "معامله‌"}, {ORTH: "مان", NORM: "مان"}],
+    "معتقدم": [{ORTH: "معتقد", NORM: "معتقد"}, {ORTH: "م", NORM: "م"}],
+    "معتقدند": [{ORTH: "معتقد", NORM: "معتقد"}, {ORTH: "ند", NORM: "ند"}],
+    "معتقدیم": [{ORTH: "معتقد", NORM: "معتقد"}, {ORTH: "یم", NORM: "یم"}],
+    "معرفی‌اش": [{ORTH: "معرفی‌", NORM: "معرفی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "معروفش": [{ORTH: "معروف", NORM: "معروف"}, {ORTH: "ش", NORM: "ش"}],
+    "معضلاتمان": [{ORTH: "معضلات", NORM: "معضلات"}, {ORTH: "مان", NORM: "مان"}],
+    "معلمش": [{ORTH: "معلم", NORM: "معلم"}, {ORTH: "ش", NORM: "ش"}],
+    "معنایش": [{ORTH: "معنای", NORM: "معنای"}, {ORTH: "ش", NORM: "ش"}],
+    "مغزشان": [{ORTH: "مغز", NORM: "مغز"}, {ORTH: "شان", NORM: "شان"}],
+    "مفیدند": [{ORTH: "مفید", NORM: "مفید"}, {ORTH: "ند", NORM: "ند"}],
+    "مقابلش": [{ORTH: "مقابل", NORM: "مقابل"}, {ORTH: "ش", NORM: "ش"}],
+    "مقاله‌اش": [{ORTH: "مقاله‌", NORM: "مقاله‌"}, {ORTH: "اش", NORM: "اش"}],
+    "مقدمش": [{ORTH: "مقدم", NORM: "مقدم"}, {ORTH: "ش", NORM: "ش"}],
+    "مقرش": [{ORTH: "مقر", NORM: "مقر"}, {ORTH: "ش", NORM: "ش"}],
+    "مقصدشان": [{ORTH: "مقصد", NORM: "مقصد"}, {ORTH: "شان", NORM: "شان"}],
+    "مقصرند": [{ORTH: "مقصر", NORM: "مقصر"}, {ORTH: "ند", NORM: "ند"}],
+    "مقصودتان": [{ORTH: "مقصود", NORM: "مقصود"}, {ORTH: "تان", NORM: "تان"}],
+    "ملاقاتهایش": [{ORTH: "ملاقاتهای", NORM: "ملاقاتهای"}, {ORTH: "ش", NORM: "ش"}],
+    "ممکنشان": [{ORTH: "ممکن", NORM: "ممکن"}, {ORTH: "شان", NORM: "شان"}],
+    "ممیزیهاست": [{ORTH: "ممیزیها", NORM: "ممیزیها"}, {ORTH: "ست", NORM: "ست"}],
+    "منظورم": [{ORTH: "منظور", NORM: "منظور"}, {ORTH: "م", NORM: "م"}],
+    "منی": [{ORTH: "من", NORM: "من"}, {ORTH: "ی", NORM: "ی"}],
+    "منید": [{ORTH: "من", NORM: "من"}, {ORTH: "ید", NORM: "ید"}],
+    "مهربانش": [{ORTH: "مهربان", NORM: "مهربان"}, {ORTH: "ش", NORM: "ش"}],
+    "مهم‌اند": [{ORTH: "مهم‌", NORM: "مهم‌"}, {ORTH: "اند", NORM: "اند"}],
+    "مواجهند": [{ORTH: "مواجه", NORM: "مواجه"}, {ORTH: "ند", NORM: "ند"}],
+    "مواجه‌اند": [{ORTH: "مواجه‌", NORM: "مواجه‌"}, {ORTH: "اند", NORM: "اند"}],
+    "مواخذه‌ات": [{ORTH: "مواخذه", NORM: "مواخذه"}, {ORTH: "‌ات", NORM: "ات"}],
+    "مواضعشان": [{ORTH: "مواضع", NORM: "مواضع"}, {ORTH: "شان", NORM: "شان"}],
+    "مواضعمان": [{ORTH: "مواضع", NORM: "مواضع"}, {ORTH: "مان", NORM: "مان"}],
+    "موافقند": [{ORTH: "موافق", NORM: "موافق"}, {ORTH: "ند", NORM: "ند"}],
+    "موجوداتش": [{ORTH: "موجودات", NORM: "موجودات"}, {ORTH: "ش", NORM: "ش"}],
+    "موجودند": [{ORTH: "موجود", NORM: "موجود"}, {ORTH: "ند", NORM: "ند"}],
+    "موردش": [{ORTH: "مورد", NORM: "مورد"}, {ORTH: "ش", NORM: "ش"}],
+    "موضعشان": [{ORTH: "موضع", NORM: "موضع"}, {ORTH: "شان", NORM: "شان"}],
+    "موظفند": [{ORTH: "موظف", NORM: "موظف"}, {ORTH: "ند", NORM: "ند"}],
+    "موهایش": [{ORTH: "موهای", NORM: "موهای"}, {ORTH: "ش", NORM: "ش"}],
+    "موهایمان": [{ORTH: "موهای", NORM: "موهای"}, {ORTH: "مان", NORM: "مان"}],
+    "مویم": [{ORTH: "مو", NORM: "مو"}, {ORTH: "یم", NORM: "یم"}],
+    "ناخرسندند": [{ORTH: "ناخرسند", NORM: "ناخرسند"}, {ORTH: "ند", NORM: "ند"}],
+    "ناراحتیش": [{ORTH: "ناراحتی", NORM: "ناراحتی"}, {ORTH: "ش", NORM: "ش"}],
+    "ناراضی‌اند": [{ORTH: "ناراضی‌", NORM: "ناراضی‌"}, {ORTH: "اند", NORM: "اند"}],
+    "نارواست": [{ORTH: "ناروا", NORM: "ناروا"}, {ORTH: "ست", NORM: "ست"}],
+    "نازش": [{ORTH: "ناز", NORM: "ناز"}, {ORTH: "ش", NORM: "ش"}],
+    "نامش": [{ORTH: "نام", NORM: "نام"}, {ORTH: "ش", NORM: "ش"}],
+    "نامشان": [{ORTH: "نام", NORM: "نام"}, {ORTH: "شان", NORM: "شان"}],
+    "نامم": [{ORTH: "نام", NORM: "نام"}, {ORTH: "م", NORM: "م"}],
+    "نامه‌ات": [{ORTH: "نامه", NORM: "نامه"}, {ORTH: "‌ات", NORM: "ات"}],
+    "نامه‌ام": [{ORTH: "نامه‌", NORM: "نامه‌"}, {ORTH: "ام", NORM: "ام"}],
+    "ناچارم": [{ORTH: "ناچار", NORM: "ناچار"}, {ORTH: "م", NORM: "م"}],
+    "نخست‌وزیری‌اش": [
+        {ORTH: "نخست‌وزیری‌", NORM: "نخست‌وزیری‌"},
+        {ORTH: "اش", NORM: "اش"},
+    ],
+    "نزدش": [{ORTH: "نزد", NORM: "نزد"}, {ORTH: "ش", NORM: "ش"}],
+    "نشانم": [{ORTH: "نشان", NORM: "نشان"}, {ORTH: "م", NORM: "م"}],
+    "نظرات‌شان": [{ORTH: "نظرات‌", NORM: "نظرات‌"}, {ORTH: "شان", NORM: "شان"}],
+    "نظرتان": [{ORTH: "نظر", NORM: "نظر"}, {ORTH: "تان", NORM: "تان"}],
+    "نظرش": [{ORTH: "نظر", NORM: "نظر"}, {ORTH: "ش", NORM: "ش"}],
+    "نظرشان": [{ORTH: "نظر", NORM: "نظر"}, {ORTH: "شان", NORM: "شان"}],
+    "نظرم": [{ORTH: "نظر", NORM: "نظر"}, {ORTH: "م", NORM: "م"}],
+    "نظرهایشان": [{ORTH: "نظرهای", NORM: "نظرهای"}, {ORTH: "شان", NORM: "شان"}],
+    "نفاقش": [{ORTH: "نفاق", NORM: "نفاق"}, {ORTH: "ش", NORM: "ش"}],
+    "نفرند": [{ORTH: "نفر", NORM: "نفر"}, {ORTH: "ند", NORM: "ند"}],
+    "نفوذیند": [{ORTH: "نفوذی", NORM: "نفوذی"}, {ORTH: "ند", NORM: "ند"}],
+    "نقطه‌نظراتتان": [
+        {ORTH: "نقطه‌نظرات", NORM: "نقطه‌نظرات"},
+        {ORTH: "تان", NORM: "تان"},
+    ],
+    "نمایشی‌مان": [{ORTH: "نمایشی‌", NORM: "نمایشی‌"}, {ORTH: "مان", NORM: "مان"}],
+    "نمایندگی‌شان": [
+        {ORTH: "نمایندگی‌", NORM: "نمایندگی‌"},
+        {ORTH: "شان", NORM: "شان"},
+    ],
+    "نمونه‌اش": [{ORTH: "نمونه‌", NORM: "نمونه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "نمی‌پذیرندش": [{ORTH: "نمی‌پذیرند", NORM: "نمی‌پذیرند"}, {ORTH: "ش", NORM: "ش"}],
+    "نوآوری‌اش": [{ORTH: "نوآوری‌", NORM: "نوآوری‌"}, {ORTH: "اش", NORM: "اش"}],
+    "نوشته‌هایشان": [
+        {ORTH: "نوشته‌های", NORM: "نوشته‌های"},
+        {ORTH: "شان", NORM: "شان"},
+    ],
+    "نوشته‌هایم": [{ORTH: "نوشته‌ها", NORM: "نوشته‌ها"}, {ORTH: "یم", NORM: "یم"}],
+    "نکردنشان": [{ORTH: "نکردن", NORM: "نکردن"}, {ORTH: "شان", NORM: "شان"}],
+    "نگاهداری‌شان": [
+        {ORTH: "نگاهداری‌", NORM: "نگاهداری‌"},
+        {ORTH: "شان", NORM: "شان"},
+    ],
+    "نگاهش": [{ORTH: "نگاه", NORM: "نگاه"}, {ORTH: "ش", NORM: "ش"}],
+    "نگرانم": [{ORTH: "نگران", NORM: "نگران"}, {ORTH: "م", NORM: "م"}],
+    "نگرشهایشان": [{ORTH: "نگرشهای", NORM: "نگرشهای"}, {ORTH: "شان", NORM: "شان"}],
+    "نیازمندند": [{ORTH: "نیازمند", NORM: "نیازمند"}, {ORTH: "ند", NORM: "ند"}],
+    "هدفش": [{ORTH: "هدف", NORM: "هدف"}, {ORTH: "ش", NORM: "ش"}],
+    "همانست": [{ORTH: "همان", NORM: "همان"}, {ORTH: "ست", NORM: "ست"}],
+    "همراهش": [{ORTH: "همراه", NORM: "همراه"}, {ORTH: "ش", NORM: "ش"}],
+    "همسرتان": [{ORTH: "همسر", NORM: "همسر"}, {ORTH: "تان", NORM: "تان"}],
+    "همسرش": [{ORTH: "همسر", NORM: "همسر"}, {ORTH: "ش", NORM: "ش"}],
+    "همسرم": [{ORTH: "همسر", NORM: "همسر"}, {ORTH: "م", NORM: "م"}],
+    "همفکرانش": [{ORTH: "همفکران", NORM: "همفکران"}, {ORTH: "ش", NORM: "ش"}],
+    "همه‌اش": [{ORTH: "همه‌", NORM: "همه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "همه‌شان": [{ORTH: "همه‌", NORM: "همه‌"}, {ORTH: "شان", NORM: "شان"}],
+    "همکارانش": [{ORTH: "همکاران", NORM: "همکاران"}, {ORTH: "ش", NORM: "ش"}],
+    "هم‌نظریم": [{ORTH: "هم‌نظر", NORM: "هم‌نظر"}, {ORTH: "یم", NORM: "یم"}],
+    "هنرش": [{ORTH: "هنر", NORM: "هنر"}, {ORTH: "ش", NORM: "ش"}],
+    "هواست": [{ORTH: "هوا", NORM: "هوا"}, {ORTH: "ست", NORM: "ست"}],
+    "هویتش": [{ORTH: "هویت", NORM: "هویت"}, {ORTH: "ش", NORM: "ش"}],
+    "وابسته‌اند": [{ORTH: "وابسته‌", NORM: "وابسته‌"}, {ORTH: "اند", NORM: "اند"}],
+    "واقفند": [{ORTH: "واقف", NORM: "واقف"}, {ORTH: "ند", NORM: "ند"}],
+    "والدینشان": [{ORTH: "والدین", NORM: "والدین"}, {ORTH: "شان", NORM: "شان"}],
+    "وجدان‌تان": [{ORTH: "وجدان‌", NORM: "وجدان‌"}, {ORTH: "تان", NORM: "تان"}],
+    "وجودشان": [{ORTH: "وجود", NORM: "وجود"}, {ORTH: "شان", NORM: "شان"}],
+    "وطنم": [{ORTH: "وطن", NORM: "وطن"}, {ORTH: "م", NORM: "م"}],
+    "وعده‌اش": [{ORTH: "وعده‌", NORM: "وعده‌"}, {ORTH: "اش", NORM: "اش"}],
+    "وقتمان": [{ORTH: "وقت", NORM: "وقت"}, {ORTH: "مان", NORM: "مان"}],
+    "ولادتش": [{ORTH: "ولادت", NORM: "ولادت"}, {ORTH: "ش", NORM: "ش"}],
+    "پایانش": [{ORTH: "پایان", NORM: "پایان"}, {ORTH: "ش", NORM: "ش"}],
+    "پایش": [{ORTH: "پای", NORM: "پای"}, {ORTH: "ش", NORM: "ش"}],
+    "پایین‌ترند": [{ORTH: "پایین‌تر", NORM: "پایین‌تر"}, {ORTH: "ند", NORM: "ند"}],
+    "پدرت": [{ORTH: "پدر", NORM: "پدر"}, {ORTH: "ت", NORM: "ت"}],
+    "پدرش": [{ORTH: "پدر", NORM: "پدر"}, {ORTH: "ش", NORM: "ش"}],
+    "پدرشان": [{ORTH: "پدر", NORM: "پدر"}, {ORTH: "شان", NORM: "شان"}],
+    "پدرم": [{ORTH: "پدر", NORM: "پدر"}, {ORTH: "م", NORM: "م"}],
+    "پربارش": [{ORTH: "پربار", NORM: "پربار"}, {ORTH: "ش", NORM: "ش"}],
+    "پروردگارت": [{ORTH: "پروردگار", NORM: "پروردگار"}, {ORTH: "ت", NORM: "ت"}],
+    "پسرتان": [{ORTH: "پسر", NORM: "پسر"}, {ORTH: "تان", NORM: "تان"}],
+    "پسرش": [{ORTH: "پسر", NORM: "پسر"}, {ORTH: "ش", NORM: "ش"}],
+    "پسرعمویش": [{ORTH: "پسرعموی", NORM: "پسرعموی"}, {ORTH: "ش", NORM: "ش"}],
+    "پسر‌عمویت": [{ORTH: "پسر‌عموی", NORM: "پسر‌عموی"}, {ORTH: "ت", NORM: "ت"}],
+    "پشتش": [{ORTH: "پشت", NORM: "پشت"}, {ORTH: "ش", NORM: "ش"}],
+    "پشیمونی": [{ORTH: "پشیمون", NORM: "پشیمون"}, {ORTH: "ی", NORM: "ی"}],
+    "پولش": [{ORTH: "پول", NORM: "پول"}, {ORTH: "ش", NORM: "ش"}],
+    "پژوهش‌هایش": [{ORTH: "پژوهش‌های", NORM: "پژوهش‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "پیامبرش": [{ORTH: "پیامبر", NORM: "پیامبر"}, {ORTH: "ش", NORM: "ش"}],
+    "پیامبری": [{ORTH: "پیامبر", NORM: "پیامبر"}, {ORTH: "ی", NORM: "ی"}],
+    "پیامش": [{ORTH: "پیام", NORM: "پیام"}, {ORTH: "ش", NORM: "ش"}],
+    "پیداست": [{ORTH: "پیدا", NORM: "پیدا"}, {ORTH: "ست", NORM: "ست"}],
+    "پیراهنش": [{ORTH: "پیراهن", NORM: "پیراهن"}, {ORTH: "ش", NORM: "ش"}],
+    "پیروانش": [{ORTH: "پیروان", NORM: "پیروان"}, {ORTH: "ش", NORM: "ش"}],
+    "پیشانی‌اش": [{ORTH: "پیشانی‌", NORM: "پیشانی‌"}, {ORTH: "اش", NORM: "اش"}],
+    "پیمانت": [{ORTH: "پیمان", NORM: "پیمان"}, {ORTH: "ت", NORM: "ت"}],
+    "پیوندشان": [{ORTH: "پیوند", NORM: "پیوند"}, {ORTH: "شان", NORM: "شان"}],
+    "چاپش": [{ORTH: "چاپ", NORM: "چاپ"}, {ORTH: "ش", NORM: "ش"}],
+    "چت": [{ORTH: "چ", NORM: "چ"}, {ORTH: "ت", NORM: "ت"}],
+    "چته": [{ORTH: "چ", NORM: "چ"}, {ORTH: "ت", NORM: "ت"}, {ORTH: "ه", NORM: "ه"}],
+    "چرخ‌هایش": [{ORTH: "چرخ‌های", NORM: "چرخ‌های"}, {ORTH: "ش", NORM: "ش"}],
+    "چشمم": [{ORTH: "چشم", NORM: "چشم"}, {ORTH: "م", NORM: "م"}],
+    "چشمهایش": [{ORTH: "چشمهای", NORM: "چشمهای"}, {ORTH: "ش", NORM: "ش"}],
+    "چشمهایشان": [{ORTH: "چشمهای", NORM: "چشمهای"}, {ORTH: "شان", NORM: "شان"}],
+    "چمنم": [{ORTH: "چمن", NORM: "چمن"}, {ORTH: "م", NORM: "م"}],
+    "چهره‌اش": [{ORTH: "چهره‌", NORM: "چهره‌"}, {ORTH: "اش", NORM: "اش"}],
+    "چکاره‌اند": [{ORTH: "چکاره‌", NORM: "چکاره‌"}, {ORTH: "اند", NORM: "اند"}],
+    "چیزهاست": [{ORTH: "چیزها", NORM: "چیزها"}, {ORTH: "ست", NORM: "ست"}],
+    "چیزهایش": [{ORTH: "چیزهای", NORM: "چیزهای"}, {ORTH: "ش", NORM: "ش"}],
+    "چیزیست": [{ORTH: "چیزی", NORM: "چیزی"}, {ORTH: "ست", NORM: "ست"}],
+    "چیست": [{ORTH: "چی", NORM: "چی"}, {ORTH: "ست", NORM: "ست"}],
+    "کارش": [{ORTH: "کار", NORM: "کار"}, {ORTH: "ش", NORM: "ش"}],
+    "کارشان": [{ORTH: "کار", NORM: "کار"}, {ORTH: "شان", NORM: "شان"}],
+    "کارم": [{ORTH: "کار", NORM: "کار"}, {ORTH: "م", NORM: "م"}],
+    "کارند": [{ORTH: "کار", NORM: "کار"}, {ORTH: "ند", NORM: "ند"}],
+    "کارهایم": [{ORTH: "کارها", NORM: "کارها"}, {ORTH: "یم", NORM: "یم"}],
+    "کافیست": [{ORTH: "کافی", NORM: "کافی"}, {ORTH: "ست", NORM: "ست"}],
+    "کتابخانه‌اش": [{ORTH: "کتابخانه‌", NORM: "کتابخانه‌"}, {ORTH: "اش", NORM: "اش"}],
+    "کتابش": [{ORTH: "کتاب", NORM: "کتاب"}, {ORTH: "ش", NORM: "ش"}],
+    "کتابهاشان": [{ORTH: "کتابها", NORM: "کتابها"}, {ORTH: "شان", NORM: "شان"}],
+    "کجاست": [{ORTH: "کجا", NORM: "کجا"}, {ORTH: "ست", NORM: "ست"}],
+    "کدورتهایشان": [{ORTH: "کدورتهای", NORM: "کدورتهای"}, {ORTH: "شان", NORM: "شان"}],
+    "کردنش": [{ORTH: "کردن", NORM: "کردن"}, {ORTH: "ش", NORM: "ش"}],
+    "کرم‌خورده‌اش": [
+        {ORTH: "کرم‌خورده‌", NORM: "کرم‌خورده‌"},
+        {ORTH: "اش", NORM: "اش"},
+    ],
+    "کشش": [{ORTH: "کش", NORM: "کش"}, {ORTH: "ش", NORM: "ش"}],
+    "کشورش": [{ORTH: "کشور", NORM: "کشور"}, {ORTH: "ش", NORM: "ش"}],
+    "کشورشان": [{ORTH: "کشور", NORM: "کشور"}, {ORTH: "شان", NORM: "شان"}],
+    "کشورمان": [{ORTH: "کشور", NORM: "کشور"}, {ORTH: "مان", NORM: "مان"}],
+    "کشورهاست": [{ORTH: "کشورها", NORM: "کشورها"}, {ORTH: "ست", NORM: "ست"}],
+    "کلیشه‌هاست": [{ORTH: "کلیشه‌ها", NORM: "کلیشه‌ها"}, {ORTH: "ست", NORM: "ست"}],
+    "کمبودهاست": [{ORTH: "کمبودها", NORM: "کمبودها"}, {ORTH: "ست", NORM: "ست"}],
+    "کمتره": [{ORTH: "کمتر", NORM: "کمتر"}, {ORTH: "ه", NORM: "ه"}],
+    "کمکم": [{ORTH: "کمک", NORM: "کمک"}, {ORTH: "م", NORM: "م"}],
+    "کنارش": [{ORTH: "کنار", NORM: "کنار"}, {ORTH: "ش", NORM: "ش"}],
+    "کودکانشان": [{ORTH: "کودکان", NORM: "کودکان"}, {ORTH: "شان", NORM: "شان"}],
+    "کوچکش": [{ORTH: "کوچک", NORM: "کوچک"}, {ORTH: "ش", NORM: "ش"}],
+    "کیست": [{ORTH: "کی", NORM: "کی"}, {ORTH: "ست", NORM: "ست"}],
+    "کیفش": [{ORTH: "کیف", NORM: "کیف"}, {ORTH: "ش", NORM: "ش"}],
+    "گذشته‌اند": [{ORTH: "گذشته‌", NORM: "گذشته‌"}, {ORTH: "اند", NORM: "اند"}],
+    "گرانقدرش": [{ORTH: "گرانقدر", NORM: "گرانقدر"}, {ORTH: "ش", NORM: "ش"}],
+    "گرانقدرشان": [{ORTH: "گرانقدر", NORM: "گرانقدر"}, {ORTH: "شان", NORM: "شان"}],
+    "گردنتان": [{ORTH: "گردن", NORM: "گردن"}, {ORTH: "تان", NORM: "تان"}],
+    "گردنش": [{ORTH: "گردن", NORM: "گردن"}, {ORTH: "ش", NORM: "ش"}],
+    "گرفتارند": [{ORTH: "گرفتار", NORM: "گرفتار"}, {ORTH: "ند", NORM: "ند"}],
+    "گرفتنت": [{ORTH: "گرفتن", NORM: "گرفتن"}, {ORTH: "ت", NORM: "ت"}],
+    "گروهند": [{ORTH: "گروه", NORM: "گروه"}, {ORTH: "ند", NORM: "ند"}],
+    "گروگانهایش": [{ORTH: "گروگانهای", NORM: "گروگانهای"}, {ORTH: "ش", NORM: "ش"}],
+    "گریمش": [{ORTH: "گریم", NORM: "گریم"}, {ORTH: "ش", NORM: "ش"}],
+    "گفتارمان": [{ORTH: "گفتار", NORM: "گفتار"}, {ORTH: "مان", NORM: "مان"}],
+    "گلهایش": [{ORTH: "گلهای", NORM: "گلهای"}, {ORTH: "ش", NORM: "ش"}],
+    "گلویش": [{ORTH: "گلوی", NORM: "گلوی"}, {ORTH: "ش", NORM: "ش"}],
+    "گناهت": [{ORTH: "گناه", NORM: "گناه"}, {ORTH: "ت", NORM: "ت"}],
+    "گوشش": [{ORTH: "گوش", NORM: "گوش"}, {ORTH: "ش", NORM: "ش"}],
+    "گوشم": [{ORTH: "گوش", NORM: "گوش"}, {ORTH: "م", NORM: "م"}],
+    "گولش": [{ORTH: "گول", NORM: "گول"}, {ORTH: "ش", NORM: "ش"}],
+    "یادتان": [{ORTH: "یاد", NORM: "یاد"}, {ORTH: "تان", NORM: "تان"}],
+    "یادم": [{ORTH: "یاد", NORM: "یاد"}, {ORTH: "م", NORM: "م"}],
+    "یادمان": [{ORTH: "یاد", NORM: "یاد"}, {ORTH: "مان", NORM: "مان"}],
+    "یارانش": [{ORTH: "یاران", NORM: "یاران"}, {ORTH: "ش", NORM: "ش"}],
 }
-
-_exc.update(
-    {
-        "آبرویت": [
-            {ORTH: "آبروی", LEMMA: "آبروی", NORM: "آبروی", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "آب‌نباتش": [
-            {ORTH: "آب‌نبات", LEMMA: "آب‌نبات", NORM: "آب‌نبات", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "آثارش": [
-            {ORTH: "آثار", LEMMA: "آثار", NORM: "آثار", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "آخرش": [
-            {ORTH: "آخر", LEMMA: "آخر", NORM: "آخر", TAG: "ADV"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "آدمهاست": [
-            {ORTH: "آدمها", LEMMA: "آدمها", NORM: "آدمها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "آرزومندیم": [
-            {ORTH: "آرزومند", LEMMA: "آرزومند", NORM: "آرزومند", TAG: "ADJ"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "آزادند": [
-            {ORTH: "آزاد", LEMMA: "آزاد", NORM: "آزاد", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "آسیب‌پذیرند": [
-            {ORTH: "آسیب‌پذیر", LEMMA: "آسیب‌پذیر", NORM: "آسیب‌پذیر", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "آفریده‌اند": [
-            {ORTH: "آفریده‌", LEMMA: "آفریده‌", NORM: "آفریده‌", TAG: "NOUN"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "آمدنش": [
-            {ORTH: "آمدن", LEMMA: "آمدن", NORM: "آمدن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "آمریکاست": [
-            {ORTH: "آمریکا", LEMMA: "آمریکا", NORM: "آمریکا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "آنجاست": [
-            {ORTH: "آنجا", LEMMA: "آنجا", NORM: "آنجا", TAG: "ADV"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "آنست": [
-            {ORTH: "آن", LEMMA: "آن", NORM: "آن", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "آنند": [
-            {ORTH: "آن", LEMMA: "آن", NORM: "آن", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "آن‌هاست": [
-            {ORTH: "آن‌ها", LEMMA: "آن‌ها", NORM: "آن‌ها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "آپاداناست": [
-            {ORTH: "آپادانا", LEMMA: "آپادانا", NORM: "آپادانا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "اجتماعی‌مان": [
-            {ORTH: "اجتماعی‌", LEMMA: "اجتماعی‌", NORM: "اجتماعی‌", TAG: "ADJ"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "اجدادت": [
-            {ORTH: "اجداد", LEMMA: "اجداد", NORM: "اجداد", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "اجدادش": [
-            {ORTH: "اجداد", LEMMA: "اجداد", NORM: "اجداد", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اجدادی‌شان": [
-            {ORTH: "اجدادی‌", LEMMA: "اجدادی‌", NORM: "اجدادی‌", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "اجراست": [
-            {ORTH: "اجرا", LEMMA: "اجرا", NORM: "اجرا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "اختیارش": [
-            {ORTH: "اختیار", LEMMA: "اختیار", NORM: "اختیار", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اخلاقشان": [
-            {ORTH: "اخلاق", LEMMA: "اخلاق", NORM: "اخلاق", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "ادعایمان": [
-            {ORTH: "ادعای", LEMMA: "ادعای", NORM: "ادعای", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "اذیتش": [
-            {ORTH: "اذیت", LEMMA: "اذیت", NORM: "اذیت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اراده‌اش": [
-            {ORTH: "اراده‌", LEMMA: "اراده‌", NORM: "اراده‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "ارتباطش": [
-            {ORTH: "ارتباط", LEMMA: "ارتباط", NORM: "ارتباط", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "ارتباطمان": [
-            {ORTH: "ارتباط", LEMMA: "ارتباط", NORM: "ارتباط", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "ارزشهاست": [
-            {ORTH: "ارزشها", LEMMA: "ارزشها", NORM: "ارزشها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "ارزی‌اش": [
-            {ORTH: "ارزی‌", LEMMA: "ارزی‌", NORM: "ارزی‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "اره‌اش": [
-            {ORTH: "اره‌", LEMMA: "اره‌", NORM: "اره‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "ازش": [
-            {ORTH: "از", LEMMA: "از", NORM: "از", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "ازین": [
-            {ORTH: "از", LEMMA: "از", NORM: "از", TAG: "ADP"},
-            {ORTH: "ین", LEMMA: "ین", NORM: "ین", TAG: "NOUN"},
-        ],
-        "ازین‌هاست": [
-            {ORTH: "از", LEMMA: "از", NORM: "از", TAG: "ADP"},
-            {ORTH: "ین‌ها", LEMMA: "ین‌ها", NORM: "ین‌ها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "استخوانند": [
-            {ORTH: "استخوان", LEMMA: "استخوان", NORM: "استخوان", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "اسلامند": [
-            {ORTH: "اسلام", LEMMA: "اسلام", NORM: "اسلام", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "اسلامی‌اند": [
-            {ORTH: "اسلامی‌", LEMMA: "اسلامی‌", NORM: "اسلامی‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "اسلحه‌هایشان": [
-            {ORTH: "اسلحه‌های", LEMMA: "اسلحه‌های", NORM: "اسلحه‌های", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "اسمت": [
-            {ORTH: "اسم", LEMMA: "اسم", NORM: "اسم", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "اسمش": [
-            {ORTH: "اسم", LEMMA: "اسم", NORM: "اسم", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اشتباهند": [
-            {ORTH: "اشتباه", LEMMA: "اشتباه", NORM: "اشتباه", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "اصلش": [
-            {ORTH: "اصل", LEMMA: "اصل", NORM: "اصل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اطاقش": [
-            {ORTH: "اطاق", LEMMA: "اطاق", NORM: "اطاق", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اعتقادند": [
-            {ORTH: "اعتقاد", LEMMA: "اعتقاد", NORM: "اعتقاد", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "اعلایش": [
-            {ORTH: "اعلای", LEMMA: "اعلای", NORM: "اعلای", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "افتراست": [
-            {ORTH: "افترا", LEMMA: "افترا", NORM: "افترا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "افطارت": [
-            {ORTH: "افطار", LEMMA: "افطار", NORM: "افطار", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "اقوامش": [
-            {ORTH: "اقوام", LEMMA: "اقوام", NORM: "اقوام", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "امروزیش": [
-            {ORTH: "امروزی", LEMMA: "امروزی", NORM: "امروزی", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اموالش": [
-            {ORTH: "اموال", LEMMA: "اموال", NORM: "اموال", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "امیدوارند": [
-            {ORTH: "امیدوار", LEMMA: "امیدوار", NORM: "امیدوار", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "امیدواریم": [
-            {ORTH: "امیدوار", LEMMA: "امیدوار", NORM: "امیدوار", TAG: "ADJ"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "انتخابهایم": [
-            {ORTH: "انتخابها", LEMMA: "انتخابها", NORM: "انتخابها", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "NOUN"},
-        ],
-        "انتظارم": [
-            {ORTH: "انتظار", LEMMA: "انتظار", NORM: "انتظار", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "انجمنم": [
-            {ORTH: "انجمن", LEMMA: "انجمن", NORM: "انجمن", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "اندرش": [
-            {ORTH: "اندر", LEMMA: "اندر", NORM: "اندر", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "انشایش": [
-            {ORTH: "انشای", LEMMA: "انشای", NORM: "انشای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "انگشتشان": [
-            {ORTH: "انگشت", LEMMA: "انگشت", NORM: "انگشت", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "انگشتهایش": [
-            {ORTH: "انگشتهای", LEMMA: "انگشتهای", NORM: "انگشتهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اهمیتشان": [
-            {ORTH: "اهمیت", LEMMA: "اهمیت", NORM: "اهمیت", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "اهمیتند": [
-            {ORTH: "اهمیت", LEMMA: "اهمیت", NORM: "اهمیت", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "اوایلش": [
-            {ORTH: "اوایل", LEMMA: "اوایل", NORM: "اوایل", TAG: "ADV"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اوست": [
-            {ORTH: "او", LEMMA: "او", NORM: "او", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "اولش": [
-            {ORTH: "اول", LEMMA: "اول", NORM: "اول", TAG: "ADV"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "اولشان": [
-            {ORTH: "اول", LEMMA: "اول", NORM: "اول", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "اولم": [
-            {ORTH: "اول", LEMMA: "اول", NORM: "اول", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "اکثرشان": [
-            {ORTH: "اکثر", LEMMA: "اکثر", NORM: "اکثر", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "ایتالیاست": [
-            {ORTH: "ایتالیا", LEMMA: "ایتالیا", NORM: "ایتالیا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "ایرانی‌اش": [
-            {ORTH: "ایرانی‌", LEMMA: "ایرانی‌", NORM: "ایرانی‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "اینجاست": [
-            {ORTH: "اینجا", LEMMA: "اینجا", NORM: "اینجا", TAG: "ADV"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "این‌هاست": [
-            {ORTH: "این‌ها", LEMMA: "این‌ها", NORM: "این‌ها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "بابات": [
-            {ORTH: "بابا", LEMMA: "بابا", NORM: "بابا", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "بارش": [
-            {ORTH: "بار", LEMMA: "بار", NORM: "بار", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بازیگرانش": [
-            {ORTH: "بازیگران", LEMMA: "بازیگران", NORM: "بازیگران", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بازیگرمان": [
-            {ORTH: "بازیگر", LEMMA: "بازیگر", NORM: "بازیگر", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "بازیگرهایم": [
-            {ORTH: "بازیگرها", LEMMA: "بازیگرها", NORM: "بازیگرها", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "NOUN"},
-        ],
-        "بازی‌اش": [
-            {ORTH: "بازی‌", LEMMA: "بازی‌", NORM: "بازی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "بالاست": [
-            {ORTH: "بالا", LEMMA: "بالا", NORM: "بالا", TAG: "ADV"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "باورند": [
-            {ORTH: "باور", LEMMA: "باور", NORM: "باور", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "بجاست": [
-            {ORTH: "بجا", LEMMA: "بجا", NORM: "بجا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "بدان": [
-            {ORTH: "ب", LEMMA: "ب", NORM: "ب", TAG: "ADP"},
-            {ORTH: "دان", LEMMA: "دان", NORM: "دان", TAG: "NOUN"},
-        ],
-        "بدش": [
-            {ORTH: "بد", LEMMA: "بد", NORM: "بد", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بدشان": [
-            {ORTH: "بد", LEMMA: "بد", NORM: "بد", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "بدنم": [
-            {ORTH: "بدن", LEMMA: "بدن", NORM: "بدن", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "بدهی‌ات": [
-            {ORTH: "بدهی‌", LEMMA: "بدهی‌", NORM: "بدهی‌", TAG: "NOUN"},
-            {ORTH: "ات", LEMMA: "ات", NORM: "ات", TAG: "NOUN"},
-        ],
-        "بدین": [
-            {ORTH: "ب", LEMMA: "ب", NORM: "ب", TAG: "ADP"},
-            {ORTH: "دین", LEMMA: "دین", NORM: "دین", TAG: "NOUN"},
-        ],
-        "برابرش": [
-            {ORTH: "برابر", LEMMA: "برابر", NORM: "برابر", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "برادرت": [
-            {ORTH: "برادر", LEMMA: "برادر", NORM: "برادر", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "برادرش": [
-            {ORTH: "برادر", LEMMA: "برادر", NORM: "برادر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "برایت": [
-            {ORTH: "برای", LEMMA: "برای", NORM: "برای", TAG: "ADP"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "برایتان": [
-            {ORTH: "برای", LEMMA: "برای", NORM: "برای", TAG: "ADP"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "برایش": [
-            {ORTH: "برای", LEMMA: "برای", NORM: "برای", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "برایشان": [
-            {ORTH: "برای", LEMMA: "برای", NORM: "برای", TAG: "ADP"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "برایم": [
-            {ORTH: "برای", LEMMA: "برای", NORM: "برای", TAG: "ADP"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "برایمان": [
-            {ORTH: "برای", LEMMA: "برای", NORM: "برای", TAG: "ADP"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "برخوردارند": [
-            {ORTH: "برخوردار", LEMMA: "برخوردار", NORM: "برخوردار", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "برنامه‌سازهاست": [
-            {
-                ORTH: "برنامه‌سازها",
-                LEMMA: "برنامه‌سازها",
-                NORM: "برنامه‌سازها",
-                TAG: "NOUN",
-            },
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "برهمش": [
-            {ORTH: "برهم", LEMMA: "برهم", NORM: "برهم", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "برهنه‌اش": [
-            {ORTH: "برهنه‌", LEMMA: "برهنه‌", NORM: "برهنه‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "برگهایش": [
-            {ORTH: "برگها", LEMMA: "برگها", NORM: "برگها", TAG: "NOUN"},
-            {ORTH: "یش", LEMMA: "یش", NORM: "یش", TAG: "NOUN"},
-        ],
-        "برین": [
-            {ORTH: "بر", LEMMA: "بر", NORM: "بر", TAG: "ADP"},
-            {ORTH: "ین", LEMMA: "ین", NORM: "ین", TAG: "NOUN"},
-        ],
-        "بزرگش": [
-            {ORTH: "بزرگ", LEMMA: "بزرگ", NORM: "بزرگ", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بزرگ‌تری": [
-            {ORTH: "بزرگ‌تر", LEMMA: "بزرگ‌تر", NORM: "بزرگ‌تر", TAG: "ADJ"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "بساطش": [
-            {ORTH: "بساط", LEMMA: "بساط", NORM: "بساط", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بعدش": [
-            {ORTH: "بعد", LEMMA: "بعد", NORM: "بعد", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بعضیهایشان": [
-            {ORTH: "بعضیهای", LEMMA: "بعضیهای", NORM: "بعضیهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "بعضی‌شان": [
-            {ORTH: "بعضی", LEMMA: "بعضی", NORM: "بعضی", TAG: "NOUN"},
-            {ORTH: "‌شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "بقیه‌اش": [
-            {ORTH: "بقیه‌", LEMMA: "بقیه‌", NORM: "بقیه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "بلندش": [
-            {ORTH: "بلند", LEMMA: "بلند", NORM: "بلند", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بناگوشش": [
-            {ORTH: "بناگوش", LEMMA: "بناگوش", NORM: "بناگوش", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بنظرم": [
-            {ORTH: "ب", LEMMA: "ب", NORM: "ب", TAG: "ADP"},
-            {ORTH: "نظر", LEMMA: "نظر", NORM: "نظر", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "بهت": [
-            {ORTH: "به", LEMMA: "به", NORM: "به", TAG: "ADP"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "بهترش": [
-            {ORTH: "بهتر", LEMMA: "بهتر", NORM: "بهتر", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بهترم": [
-            {ORTH: "بهتر", LEMMA: "بهتر", NORM: "بهتر", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "بهتری": [
-            {ORTH: "بهتر", LEMMA: "بهتر", NORM: "بهتر", TAG: "ADJ"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "بهش": [
-            {ORTH: "به", LEMMA: "به", NORM: "به", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "به‌شان": [
-            {ORTH: "به‌", LEMMA: "به‌", NORM: "به‌", TAG: "ADP"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "بودمش": [
-            {ORTH: "بودم", LEMMA: "بودم", NORM: "بودم", TAG: "VERB"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بودنش": [
-            {ORTH: "بودن", LEMMA: "بودن", NORM: "بودن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بودن‌شان": [
-            {ORTH: "بودن‌", LEMMA: "بودن‌", NORM: "بودن‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "بوستانش": [
-            {ORTH: "بوستان", LEMMA: "بوستان", NORM: "بوستان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بویش": [
-            {ORTH: "بو", LEMMA: "بو", NORM: "بو", TAG: "NOUN"},
-            {ORTH: "یش", LEMMA: "یش", NORM: "یش", TAG: "NOUN"},
-        ],
-        "بچه‌اش": [
-            {ORTH: "بچه‌", LEMMA: "بچه‌", NORM: "بچه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "بچه‌م": [
-            {ORTH: "بچه‌", LEMMA: "بچه‌", NORM: "بچه‌", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "بچه‌هایش": [
-            {ORTH: "بچه‌های", LEMMA: "بچه‌های", NORM: "بچه‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بیانیه‌شان": [
-            {ORTH: "بیانیه‌", LEMMA: "بیانیه‌", NORM: "بیانیه‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "بیدارم": [
-            {ORTH: "بیدار", LEMMA: "بیدار", NORM: "بیدار", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "بیناتری": [
-            {ORTH: "بیناتر", LEMMA: "بیناتر", NORM: "بیناتر", TAG: "ADJ"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "بی‌اطلاعند": [
-            {ORTH: "بی‌اطلاع", LEMMA: "بی‌اطلاع", NORM: "بی‌اطلاع", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "بی‌اطلاعید": [
-            {ORTH: "بی‌اطلاع", LEMMA: "بی‌اطلاع", NORM: "بی‌اطلاع", TAG: "ADJ"},
-            {ORTH: "ید", LEMMA: "ید", NORM: "ید", TAG: "VERB"},
-        ],
-        "بی‌بهره‌اند": [
-            {ORTH: "بی‌بهره‌", LEMMA: "بی‌بهره‌", NORM: "بی‌بهره‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "بی‌تفاوتند": [
-            {ORTH: "بی‌تفاوت", LEMMA: "بی‌تفاوت", NORM: "بی‌تفاوت", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "بی‌حسابش": [
-            {ORTH: "بی‌حساب", LEMMA: "بی‌حساب", NORM: "بی‌حساب", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "بی‌نیش": [
-            {ORTH: "بی‌نی", LEMMA: "بی‌نی", NORM: "بی‌نی", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "تجربه‌هایم": [
-            {ORTH: "تجربه‌ها", LEMMA: "تجربه‌ها", NORM: "تجربه‌ها", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "NOUN"},
-        ],
-        "تحریم‌هاست": [
-            {ORTH: "تحریم‌ها", LEMMA: "تحریم‌ها", NORM: "تحریم‌ها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "تحولند": [
-            {ORTH: "تحول", LEMMA: "تحول", NORM: "تحول", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "تخیلی‌اش": [
-            {ORTH: "تخیلی‌", LEMMA: "تخیلی‌", NORM: "تخیلی‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "ترا": [
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-            {ORTH: "را", LEMMA: "را", NORM: "را", TAG: "PART"},
-        ],
-        "ترسشان": [
-            {ORTH: "ترس", LEMMA: "ترس", NORM: "ترس", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "ترکش": [
-            {ORTH: "ترک", LEMMA: "ترک", NORM: "ترک", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "تشنه‌ت": [
-            {ORTH: "تشنه‌", LEMMA: "تشنه‌", NORM: "تشنه‌", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "تشکیلاتی‌اش": [
-            {ORTH: "تشکیلاتی‌", LEMMA: "تشکیلاتی‌", NORM: "تشکیلاتی‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "تعلقش": [
-            {ORTH: "تعلق", LEMMA: "تعلق", NORM: "تعلق", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "تلاششان": [
-            {ORTH: "تلاش", LEMMA: "تلاش", NORM: "تلاش", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "تلاشمان": [
-            {ORTH: "تلاش", LEMMA: "تلاش", NORM: "تلاش", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "تماشاگرش": [
-            {ORTH: "تماشاگر", LEMMA: "تماشاگر", NORM: "تماشاگر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "تمامشان": [
-            {ORTH: "تمام", LEMMA: "تمام", NORM: "تمام", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "تنش": [
-            {ORTH: "تن", LEMMA: "تن", NORM: "تن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "تنمان": [
-            {ORTH: "تن", LEMMA: "تن", NORM: "تن", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "تنهایی‌اش": [
-            {ORTH: "تنهایی‌", LEMMA: "تنهایی‌", NORM: "تنهایی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "توانایی‌اش": [
-            {ORTH: "توانایی‌", LEMMA: "توانایی‌", NORM: "توانایی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "توجهش": [
-            {ORTH: "توجه", LEMMA: "توجه", NORM: "توجه", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "توست": [
-            {ORTH: "تو", LEMMA: "تو", NORM: "تو", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "توصیه‌اش": [
-            {ORTH: "توصیه‌", LEMMA: "توصیه‌", NORM: "توصیه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "تیغه‌اش": [
-            {ORTH: "تیغه‌", LEMMA: "تیغه‌", NORM: "تیغه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "جاست": [
-            {ORTH: "جا", LEMMA: "جا", NORM: "جا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "جامعه‌اند": [
-            {ORTH: "جامعه‌", LEMMA: "جامعه‌", NORM: "جامعه‌", TAG: "NOUN"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "جانم": [
-            {ORTH: "جان", LEMMA: "جان", NORM: "جان", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "جایش": [
-            {ORTH: "جای", LEMMA: "جای", NORM: "جای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "جایشان": [
-            {ORTH: "جای", LEMMA: "جای", NORM: "جای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "جدیدش": [
-            {ORTH: "جدید", LEMMA: "جدید", NORM: "جدید", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "جرمزاست": [
-            {ORTH: "جرمزا", LEMMA: "جرمزا", NORM: "جرمزا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "جلوست": [
-            {ORTH: "جلو", LEMMA: "جلو", NORM: "جلو", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "جلویش": [
-            {ORTH: "جلوی", LEMMA: "جلوی", NORM: "جلوی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "جمهوریست": [
-            {ORTH: "جمهوری", LEMMA: "جمهوری", NORM: "جمهوری", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "جنسش": [
-            {ORTH: "جنس", LEMMA: "جنس", NORM: "جنس", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "جنس‌اند": [
-            {ORTH: "جنس‌", LEMMA: "جنس‌", NORM: "جنس‌", TAG: "NOUN"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "جوانانش": [
-            {ORTH: "جوانان", LEMMA: "جوانان", NORM: "جوانان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "جویش": [
-            {ORTH: "جوی", LEMMA: "جوی", NORM: "جوی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "جگرش": [
-            {ORTH: "جگر", LEMMA: "جگر", NORM: "جگر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "حاضرم": [
-            {ORTH: "حاضر", LEMMA: "حاضر", NORM: "حاضر", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "حالتهایشان": [
-            {ORTH: "حالتهای", LEMMA: "حالتهای", NORM: "حالتهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "حالیست": [
-            {ORTH: "حالی", LEMMA: "حالی", NORM: "حالی", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "حالی‌مان": [
-            {ORTH: "حالی‌", LEMMA: "حالی‌", NORM: "حالی‌", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "حاکیست": [
-            {ORTH: "حاکی", LEMMA: "حاکی", NORM: "حاکی", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "حرامزادگی‌اش": [
-            {ORTH: "حرامزادگی‌", LEMMA: "حرامزادگی‌", NORM: "حرامزادگی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "حرفتان": [
-            {ORTH: "حرف", LEMMA: "حرف", NORM: "حرف", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "حرفش": [
-            {ORTH: "حرف", LEMMA: "حرف", NORM: "حرف", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "حرفشان": [
-            {ORTH: "حرف", LEMMA: "حرف", NORM: "حرف", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "حرفم": [
-            {ORTH: "حرف", LEMMA: "حرف", NORM: "حرف", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "حرف‌های‌شان": [
-            {ORTH: "حرف‌های‌", LEMMA: "حرف‌های‌", NORM: "حرف‌های‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "حرکتمان": [
-            {ORTH: "حرکت", LEMMA: "حرکت", NORM: "حرکت", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "حریفانشان": [
-            {ORTH: "حریفان", LEMMA: "حریفان", NORM: "حریفان", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "حضورشان": [
-            {ORTH: "حضور", LEMMA: "حضور", NORM: "حضور", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "حمایتش": [
-            {ORTH: "حمایت", LEMMA: "حمایت", NORM: "حمایت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "حواسش": [
-            {ORTH: "حواس", LEMMA: "حواس", NORM: "حواس", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "حواسشان": [
-            {ORTH: "حواس", LEMMA: "حواس", NORM: "حواس", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "حوصله‌مان": [
-            {ORTH: "حوصله‌", LEMMA: "حوصله‌", NORM: "حوصله‌", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "حکومتش": [
-            {ORTH: "حکومت", LEMMA: "حکومت", NORM: "حکومت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "حکومتشان": [
-            {ORTH: "حکومت", LEMMA: "حکومت", NORM: "حکومت", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "حیفم": [
-            {ORTH: "حیف", LEMMA: "حیف", NORM: "حیف", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "خاندانش": [
-            {ORTH: "خاندان", LEMMA: "خاندان", NORM: "خاندان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خانه‌اش": [
-            {ORTH: "خانه‌", LEMMA: "خانه‌", NORM: "خانه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "خانه‌شان": [
-            {ORTH: "خانه‌", LEMMA: "خانه‌", NORM: "خانه‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خانه‌مان": [
-            {ORTH: "خانه‌", LEMMA: "خانه‌", NORM: "خانه‌", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "خانه‌هایشان": [
-            {ORTH: "خانه‌های", LEMMA: "خانه‌های", NORM: "خانه‌های", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خانواده‌ات": [
-            {ORTH: "خانواده", LEMMA: "خانواده", NORM: "خانواده", TAG: "NOUN"},
-            {ORTH: "‌ات", LEMMA: "ات", NORM: "ات", TAG: "NOUN"},
-        ],
-        "خانواده‌اش": [
-            {ORTH: "خانواده‌", LEMMA: "خانواده‌", NORM: "خانواده‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "خانواده‌ام": [
-            {ORTH: "خانواده‌", LEMMA: "خانواده‌", NORM: "خانواده‌", TAG: "NOUN"},
-            {ORTH: "ام", LEMMA: "ام", NORM: "ام", TAG: "NOUN"},
-        ],
-        "خانواده‌شان": [
-            {ORTH: "خانواده‌", LEMMA: "خانواده‌", NORM: "خانواده‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خداست": [
-            {ORTH: "خدا", LEMMA: "خدا", NORM: "خدا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "خدایش": [
-            {ORTH: "خدا", LEMMA: "خدا", NORM: "خدا", TAG: "NOUN"},
-            {ORTH: "یش", LEMMA: "یش", NORM: "یش", TAG: "NOUN"},
-        ],
-        "خدایشان": [
-            {ORTH: "خدای", LEMMA: "خدای", NORM: "خدای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خردسالش": [
-            {ORTH: "خردسال", LEMMA: "خردسال", NORM: "خردسال", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خروپفشان": [
-            {ORTH: "خروپف", LEMMA: "خروپف", NORM: "خروپف", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خسته‌ای": [
-            {ORTH: "خسته‌", LEMMA: "خسته‌", NORM: "خسته‌", TAG: "ADJ"},
-            {ORTH: "ای", LEMMA: "ای", NORM: "ای", TAG: "VERB"},
-        ],
-        "خطت": [
-            {ORTH: "خط", LEMMA: "خط", NORM: "خط", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "خوابمان": [
-            {ORTH: "خواب", LEMMA: "خواب", NORM: "خواب", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "خواندنش": [
-            {ORTH: "خواندن", LEMMA: "خواندن", NORM: "خواندن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خواهرش": [
-            {ORTH: "خواهر", LEMMA: "خواهر", NORM: "خواهر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خوبش": [
-            {ORTH: "خوب", LEMMA: "خوب", NORM: "خوب", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خودت": [
-            {ORTH: "خود", LEMMA: "خود", NORM: "خود", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "خودتان": [
-            {ORTH: "خود", LEMMA: "خود", NORM: "خود", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "خودش": [
-            {ORTH: "خود", LEMMA: "خود", NORM: "خود", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خودشان": [
-            {ORTH: "خود", LEMMA: "خود", NORM: "خود", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خودمان": [
-            {ORTH: "خود", LEMMA: "خود", NORM: "خود", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "خوردمان": [
-            {ORTH: "خورد", LEMMA: "خورد", NORM: "خورد", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "خوردنشان": [
-            {ORTH: "خوردن", LEMMA: "خوردن", NORM: "خوردن", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خوشش": [
-            {ORTH: "خوش", LEMMA: "خوش", NORM: "خوش", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خوشوقتم": [
-            {ORTH: "خوشوقت", LEMMA: "خوشوقت", NORM: "خوشوقت", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "خونشان": [
-            {ORTH: "خون", LEMMA: "خون", NORM: "خون", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "خویش": [
-            {ORTH: "خوی", LEMMA: "خوی", NORM: "خوی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خویشتنم": [
-            {ORTH: "خویشتن", LEMMA: "خویشتن", NORM: "خویشتن", TAG: "VERB"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "خیالش": [
-            {ORTH: "خیال", LEMMA: "خیال", NORM: "خیال", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "خیسش": [
-            {ORTH: "خیس", LEMMA: "خیس", NORM: "خیس", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "داراست": [
-            {ORTH: "دارا", LEMMA: "دارا", NORM: "دارا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "داستانهایش": [
-            {ORTH: "داستانهای", LEMMA: "داستانهای", NORM: "داستانهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دخترمان": [
-            {ORTH: "دختر", LEMMA: "دختر", NORM: "دختر", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "دخیلند": [
-            {ORTH: "دخیل", LEMMA: "دخیل", NORM: "دخیل", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "درباره‌ات": [
-            {ORTH: "درباره", LEMMA: "درباره", NORM: "درباره", TAG: "ADP"},
-            {ORTH: "‌ات", LEMMA: "ات", NORM: "ات", TAG: "NOUN"},
-        ],
-        "درباره‌اش": [
-            {ORTH: "درباره‌", LEMMA: "درباره‌", NORM: "درباره‌", TAG: "ADP"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "دردش": [
-            {ORTH: "درد", LEMMA: "درد", NORM: "درد", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دردشان": [
-            {ORTH: "درد", LEMMA: "درد", NORM: "درد", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "درسته": [
-            {ORTH: "درست", LEMMA: "درست", NORM: "درست", TAG: "ADJ"},
-            {ORTH: "ه", LEMMA: "ه", NORM: "ه", TAG: "VERB"},
-        ],
-        "درش": [
-            {ORTH: "در", LEMMA: "در", NORM: "در", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "درون‌شان": [
-            {ORTH: "درون‌", LEMMA: "درون‌", NORM: "درون‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "درین": [
-            {ORTH: "در", LEMMA: "در", NORM: "در", TAG: "ADP"},
-            {ORTH: "ین", LEMMA: "ین", NORM: "ین", TAG: "NOUN"},
-        ],
-        "دریچه‌هایش": [
-            {ORTH: "دریچه‌های", LEMMA: "دریچه‌های", NORM: "دریچه‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دزدانش": [
-            {ORTH: "دزدان", LEMMA: "دزدان", NORM: "دزدان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دستت": [
-            {ORTH: "دست", LEMMA: "دست", NORM: "دست", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "دستش": [
-            {ORTH: "دست", LEMMA: "دست", NORM: "دست", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دستمان": [
-            {ORTH: "دست", LEMMA: "دست", NORM: "دست", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "دستهایشان": [
-            {ORTH: "دستهای", LEMMA: "دستهای", NORM: "دستهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "دست‌یافتنی‌ست": [
-            {
-                ORTH: "دست‌یافتنی‌",
-                LEMMA: "دست‌یافتنی‌",
-                NORM: "دست‌یافتنی‌",
-                TAG: "ADJ",
-            },
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "دشمنند": [
-            {ORTH: "دشمن", LEMMA: "دشمن", NORM: "دشمن", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "دشمنیشان": [
-            {ORTH: "دشمنی", LEMMA: "دشمنی", NORM: "دشمنی", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "دشمنیم": [
-            {ORTH: "دشمن", LEMMA: "دشمن", NORM: "دشمن", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "دفترش": [
-            {ORTH: "دفتر", LEMMA: "دفتر", NORM: "دفتر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دفنشان": [
-            {ORTH: "دفن", LEMMA: "دفن", NORM: "دفن", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "دلت": [
-            {ORTH: "دل", LEMMA: "دل", NORM: "دل", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "دلش": [
-            {ORTH: "دل", LEMMA: "دل", NORM: "دل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دلشان": [
-            {ORTH: "دل", LEMMA: "دل", NORM: "دل", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "دلم": [
-            {ORTH: "دل", LEMMA: "دل", NORM: "دل", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "دلیلش": [
-            {ORTH: "دلیل", LEMMA: "دلیل", NORM: "دلیل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دنبالش": [
-            {ORTH: "دنبال", LEMMA: "دنبال", NORM: "دنبال", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دنباله‌اش": [
-            {ORTH: "دنباله‌", LEMMA: "دنباله‌", NORM: "دنباله‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "دهاتی‌هایش": [
-            {ORTH: "دهاتی‌های", LEMMA: "دهاتی‌های", NORM: "دهاتی‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دهانت": [
-            {ORTH: "دهان", LEMMA: "دهان", NORM: "دهان", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "دهنش": [
-            {ORTH: "دهن", LEMMA: "دهن", NORM: "دهن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دورش": [
-            {ORTH: "دور", LEMMA: "دور", NORM: "دور", TAG: "ADV"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دوروبریهاشان": [
-            {ORTH: "دوروبریها", LEMMA: "دوروبریها", NORM: "دوروبریها", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "دوستانش": [
-            {ORTH: "دوستان", LEMMA: "دوستان", NORM: "دوستان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دوستانشان": [
-            {ORTH: "دوستان", LEMMA: "دوستان", NORM: "دوستان", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "دوستت": [
-            {ORTH: "دوست", LEMMA: "دوست", NORM: "دوست", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "دوستش": [
-            {ORTH: "دوست", LEMMA: "دوست", NORM: "دوست", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دومش": [
-            {ORTH: "دوم", LEMMA: "دوم", NORM: "دوم", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دویدنش": [
-            {ORTH: "دویدن", LEMMA: "دویدن", NORM: "دویدن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دکورهایمان": [
-            {ORTH: "دکورهای", LEMMA: "دکورهای", NORM: "دکورهای", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "دیدگاهش": [
-            {ORTH: "دیدگاه", LEMMA: "دیدگاه", NORM: "دیدگاه", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دیرت": [
-            {ORTH: "دیر", LEMMA: "دیر", NORM: "دیر", TAG: "ADV"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "دیرم": [
-            {ORTH: "دیر", LEMMA: "دیر", NORM: "دیر", TAG: "ADV"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "دینت": [
-            {ORTH: "دین", LEMMA: "دین", NORM: "دین", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "دینش": [
-            {ORTH: "دین", LEMMA: "دین", NORM: "دین", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دین‌شان": [
-            {ORTH: "دین‌", LEMMA: "دین‌", NORM: "دین‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "دیواره‌هایش": [
-            {ORTH: "دیواره‌های", LEMMA: "دیواره‌های", NORM: "دیواره‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "دیوانه‌ای": [
-            {ORTH: "دیوانه‌", LEMMA: "دیوانه‌", NORM: "دیوانه‌", TAG: "ADJ"},
-            {ORTH: "ای", LEMMA: "ای", NORM: "ای", TAG: "VERB"},
-        ],
-        "دیوی": [
-            {ORTH: "دیو", LEMMA: "دیو", NORM: "دیو", TAG: "NOUN"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "دیگرم": [
-            {ORTH: "دیگر", LEMMA: "دیگر", NORM: "دیگر", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "دیگرمان": [
-            {ORTH: "دیگر", LEMMA: "دیگر", NORM: "دیگر", TAG: "ADJ"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "ذهنش": [
-            {ORTH: "ذهن", LEMMA: "ذهن", NORM: "ذهن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "ذهنشان": [
-            {ORTH: "ذهن", LEMMA: "ذهن", NORM: "ذهن", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "ذهنم": [
-            {ORTH: "ذهن", LEMMA: "ذهن", NORM: "ذهن", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "رئوسش": [
-            {ORTH: "رئوس", LEMMA: "رئوس", NORM: "رئوس", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "راهشان": [
-            {ORTH: "راه", LEMMA: "راه", NORM: "راه", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "راهگشاست": [
-            {ORTH: "راهگشا", LEMMA: "راهگشا", NORM: "راهگشا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "رایانه‌هایشان": [
-            {ORTH: "رایانه‌های", LEMMA: "رایانه‌های", NORM: "رایانه‌های", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "رعایتشان": [
-            {ORTH: "رعایت", LEMMA: "رعایت", NORM: "رعایت", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "رفتارش": [
-            {ORTH: "رفتار", LEMMA: "رفتار", NORM: "رفتار", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "رفتارشان": [
-            {ORTH: "رفتار", LEMMA: "رفتار", NORM: "رفتار", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "رفتارمان": [
-            {ORTH: "رفتار", LEMMA: "رفتار", NORM: "رفتار", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "رفتارهاست": [
-            {ORTH: "رفتارها", LEMMA: "رفتارها", NORM: "رفتارها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "رفتارهایشان": [
-            {ORTH: "رفتارهای", LEMMA: "رفتارهای", NORM: "رفتارهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "رفقایم": [
-            {ORTH: "رفقا", LEMMA: "رفقا", NORM: "رفقا", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "NOUN"},
-        ],
-        "رقیق‌ترش": [
-            {ORTH: "رقیق‌تر", LEMMA: "رقیق‌تر", NORM: "رقیق‌تر", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "رنجند": [
-            {ORTH: "رنج", LEMMA: "رنج", NORM: "رنج", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "رهگشاست": [
-            {ORTH: "رهگشا", LEMMA: "رهگشا", NORM: "رهگشا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "رواست": [
-            {ORTH: "روا", LEMMA: "روا", NORM: "روا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "روبروست": [
-            {ORTH: "روبرو", LEMMA: "روبرو", NORM: "روبرو", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "روحی‌اش": [
-            {ORTH: "روحی‌", LEMMA: "روحی‌", NORM: "روحی‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "روزنامه‌اش": [
-            {ORTH: "روزنامه‌", LEMMA: "روزنامه‌", NORM: "روزنامه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "روزه‌ست": [
-            {ORTH: "روزه‌", LEMMA: "روزه‌", NORM: "روزه‌", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "روسری‌اش": [
-            {ORTH: "روسری‌", LEMMA: "روسری‌", NORM: "روسری‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "روشتان": [
-            {ORTH: "روش", LEMMA: "روش", NORM: "روش", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "رویش": [
-            {ORTH: "روی", LEMMA: "روی", NORM: "روی", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "زبانش": [
-            {ORTH: "زبان", LEMMA: "زبان", NORM: "زبان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "زحماتشان": [
-            {ORTH: "زحمات", LEMMA: "زحمات", NORM: "زحمات", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "زدنهایشان": [
-            {ORTH: "زدنهای", LEMMA: "زدنهای", NORM: "زدنهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "زرنگشان": [
-            {ORTH: "زرنگ", LEMMA: "زرنگ", NORM: "زرنگ", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "زشتش": [
-            {ORTH: "زشت", LEMMA: "زشت", NORM: "زشت", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "زشتکارانند": [
-            {ORTH: "زشتکاران", LEMMA: "زشتکاران", NORM: "زشتکاران", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "زلفش": [
-            {ORTH: "زلف", LEMMA: "زلف", NORM: "زلف", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "زمن": [
-            {ORTH: "ز", LEMMA: "ز", NORM: "ز", TAG: "ADP"},
-            {ORTH: "من", LEMMA: "من", NORM: "من", TAG: "NOUN"},
-        ],
-        "زنبوری‌اش": [
-            {ORTH: "زنبوری‌", LEMMA: "زنبوری‌", NORM: "زنبوری‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "زندانم": [
-            {ORTH: "زندان", LEMMA: "زندان", NORM: "زندان", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "زنده‌ام": [
-            {ORTH: "زنده‌", LEMMA: "زنده‌", NORM: "زنده‌", TAG: "ADJ"},
-            {ORTH: "ام", LEMMA: "ام", NORM: "ام", TAG: "VERB"},
-        ],
-        "زندگانی‌اش": [
-            {ORTH: "زندگانی‌", LEMMA: "زندگانی‌", NORM: "زندگانی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "زندگی‌اش": [
-            {ORTH: "زندگی‌", LEMMA: "زندگی‌", NORM: "زندگی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "زندگی‌ام": [
-            {ORTH: "زندگی‌", LEMMA: "زندگی‌", NORM: "زندگی‌", TAG: "NOUN"},
-            {ORTH: "ام", LEMMA: "ام", NORM: "ام", TAG: "NOUN"},
-        ],
-        "زندگی‌شان": [
-            {ORTH: "زندگی‌", LEMMA: "زندگی‌", NORM: "زندگی‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "زنش": [
-            {ORTH: "زن", LEMMA: "زن", NORM: "زن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "زنند": [
-            {ORTH: "زن", LEMMA: "زن", NORM: "زن", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "زو": [
-            {ORTH: "ز", LEMMA: "ز", NORM: "ز", TAG: "ADP"},
-            {ORTH: "و", LEMMA: "و", NORM: "و", TAG: "NOUN"},
-        ],
-        "زیاده": [
-            {ORTH: "زیاد", LEMMA: "زیاد", NORM: "زیاد", TAG: "ADJ"},
-            {ORTH: "ه", LEMMA: "ه", NORM: "ه", TAG: "VERB"},
-        ],
-        "زیباست": [
-            {ORTH: "زیبا", LEMMA: "زیبا", NORM: "زیبا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "زیبایش": [
-            {ORTH: "زیبای", LEMMA: "زیبای", NORM: "زیبای", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "زیبایی": [
-            {ORTH: "زیبای", LEMMA: "زیبای", NORM: "زیبای", TAG: "ADJ"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "زیربناست": [
-            {ORTH: "زیربنا", LEMMA: "زیربنا", NORM: "زیربنا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "زیرک‌اند": [
-            {ORTH: "زیرک‌", LEMMA: "زیرک‌", NORM: "زیرک‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "سؤالتان": [
-            {ORTH: "سؤال", LEMMA: "سؤال", NORM: "سؤال", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "سؤالم": [
-            {ORTH: "سؤال", LEMMA: "سؤال", NORM: "سؤال", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "سابقه‌اش": [
-            {ORTH: "سابقه‌", LEMMA: "سابقه‌", NORM: "سابقه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "ساختنم": [
-            {ORTH: "ساختن", LEMMA: "ساختن", NORM: "ساختن", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "ساده‌اش": [
-            {ORTH: "ساده‌", LEMMA: "ساده‌", NORM: "ساده‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "ساده‌اند": [
-            {ORTH: "ساده‌", LEMMA: "ساده‌", NORM: "ساده‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "سازمانش": [
-            {ORTH: "سازمان", LEMMA: "سازمان", NORM: "سازمان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "ساعتم": [
-            {ORTH: "ساعت", LEMMA: "ساعت", NORM: "ساعت", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "سالته": [
-            {ORTH: "سال", LEMMA: "سال", NORM: "سال", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-            {ORTH: "ه", LEMMA: "ه", NORM: "ه", TAG: "VERB"},
-        ],
-        "سالش": [
-            {ORTH: "سال", LEMMA: "سال", NORM: "سال", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سالهاست": [
-            {ORTH: "سالها", LEMMA: "سالها", NORM: "سالها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "ساله‌اش": [
-            {ORTH: "ساله‌", LEMMA: "ساله‌", NORM: "ساله‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "ساکتند": [
-            {ORTH: "ساکت", LEMMA: "ساکت", NORM: "ساکت", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "ساکنند": [
-            {ORTH: "ساکن", LEMMA: "ساکن", NORM: "ساکن", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "سبزشان": [
-            {ORTH: "سبز", LEMMA: "سبز", NORM: "سبز", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "سبیل‌مان": [
-            {ORTH: "سبیل‌", LEMMA: "سبیل‌", NORM: "سبیل‌", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "ستم‌هایش": [
-            {ORTH: "ستم‌های", LEMMA: "ستم‌های", NORM: "ستم‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سخنانش": [
-            {ORTH: "سخنان", LEMMA: "سخنان", NORM: "سخنان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سخنانشان": [
-            {ORTH: "سخنان", LEMMA: "سخنان", NORM: "سخنان", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "سخنتان": [
-            {ORTH: "سخن", LEMMA: "سخن", NORM: "سخن", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "سخنش": [
-            {ORTH: "سخن", LEMMA: "سخن", NORM: "سخن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سخنم": [
-            {ORTH: "سخن", LEMMA: "سخن", NORM: "سخن", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "سردش": [
-            {ORTH: "سرد", LEMMA: "سرد", NORM: "سرد", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سرزمینشان": [
-            {ORTH: "سرزمین", LEMMA: "سرزمین", NORM: "سرزمین", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "سرش": [
-            {ORTH: "سر", LEMMA: "سر", NORM: "سر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سرمایه‌دارهاست": [
-            {
-                ORTH: "سرمایه‌دارها",
-                LEMMA: "سرمایه‌دارها",
-                NORM: "سرمایه‌دارها",
-                TAG: "NOUN",
-            },
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "سرنوشتش": [
-            {ORTH: "سرنوشت", LEMMA: "سرنوشت", NORM: "سرنوشت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سرنوشتشان": [
-            {ORTH: "سرنوشت", LEMMA: "سرنوشت", NORM: "سرنوشت", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "سروتهش": [
-            {ORTH: "سروته", LEMMA: "سروته", NORM: "سروته", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سرچشمه‌اش": [
-            {ORTH: "سرچشمه‌", LEMMA: "سرچشمه‌", NORM: "سرچشمه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "سقمش": [
-            {ORTH: "سقم", LEMMA: "سقم", NORM: "سقم", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سنش": [
-            {ORTH: "سن", LEMMA: "سن", NORM: "سن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سپاهش": [
-            {ORTH: "سپاه", LEMMA: "سپاه", NORM: "سپاه", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "سیاسیشان": [
-            {ORTH: "سیاسی", LEMMA: "سیاسی", NORM: "سیاسی", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "سیاه‌چاله‌هاست": [
-            {
-                ORTH: "سیاه‌چاله‌ها",
-                LEMMA: "سیاه‌چاله‌ها",
-                NORM: "سیاه‌چاله‌ها",
-                TAG: "NOUN",
-            },
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "شاخه‌هایشان": [
-            {ORTH: "شاخه‌های", LEMMA: "شاخه‌های", NORM: "شاخه‌های", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "شالوده‌اش": [
-            {ORTH: "شالوده‌", LEMMA: "شالوده‌", NORM: "شالوده‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "شانه‌هایش": [
-            {ORTH: "شانه‌های", LEMMA: "شانه‌های", NORM: "شانه‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شاهدیم": [
-            {ORTH: "شاهد", LEMMA: "شاهد", NORM: "شاهد", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "شاهکارهایش": [
-            {ORTH: "شاهکارهای", LEMMA: "شاهکارهای", NORM: "شاهکارهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شخصیتش": [
-            {ORTH: "شخصیت", LEMMA: "شخصیت", NORM: "شخصیت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شدنشان": [
-            {ORTH: "شدن", LEMMA: "شدن", NORM: "شدن", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "شرکتیست": [
-            {ORTH: "شرکتی", LEMMA: "شرکتی", NORM: "شرکتی", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "شعارهاشان": [
-            {ORTH: "شعارها", LEMMA: "شعارها", NORM: "شعارها", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "شعورش": [
-            {ORTH: "شعور", LEMMA: "شعور", NORM: "شعور", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شغلش": [
-            {ORTH: "شغل", LEMMA: "شغل", NORM: "شغل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شماست": [
-            {ORTH: "شما", LEMMA: "شما", NORM: "شما", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "شمشیرش": [
-            {ORTH: "شمشیر", LEMMA: "شمشیر", NORM: "شمشیر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شنیدنش": [
-            {ORTH: "شنیدن", LEMMA: "شنیدن", NORM: "شنیدن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شوراست": [
-            {ORTH: "شورا", LEMMA: "شورا", NORM: "شورا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "شومت": [
-            {ORTH: "شوم", LEMMA: "شوم", NORM: "شوم", TAG: "ADJ"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "شیرینترش": [
-            {ORTH: "شیرینتر", LEMMA: "شیرینتر", NORM: "شیرینتر", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "شیطان‌اند": [
-            {ORTH: "شیطان‌", LEMMA: "شیطان‌", NORM: "شیطان‌", TAG: "NOUN"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "شیوه‌هاست": [
-            {ORTH: "شیوه‌ها", LEMMA: "شیوه‌ها", NORM: "شیوه‌ها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "صاحبش": [
-            {ORTH: "صاحب", LEMMA: "صاحب", NORM: "صاحب", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "صحنه‌اش": [
-            {ORTH: "صحنه‌", LEMMA: "صحنه‌", NORM: "صحنه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "صدایش": [
-            {ORTH: "صدای", LEMMA: "صدای", NORM: "صدای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "صددند": [
-            {ORTH: "صدد", LEMMA: "صدد", NORM: "صدد", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "صندوق‌هاست": [
-            {ORTH: "صندوق‌ها", LEMMA: "صندوق‌ها", NORM: "صندوق‌ها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "صندوق‌هایش": [
-            {ORTH: "صندوق‌های", LEMMA: "صندوق‌های", NORM: "صندوق‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "صورتش": [
-            {ORTH: "صورت", LEMMA: "صورت", NORM: "صورت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "ضروری‌اند": [
-            {ORTH: "ضروری‌", LEMMA: "ضروری‌", NORM: "ضروری‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "ضمیرش": [
-            {ORTH: "ضمیر", LEMMA: "ضمیر", NORM: "ضمیر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "طرفش": [
-            {ORTH: "طرف", LEMMA: "طرف", NORM: "طرف", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "طلسمش": [
-            {ORTH: "طلسم", LEMMA: "طلسم", NORM: "طلسم", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "طوره": [
-            {ORTH: "طور", LEMMA: "طور", NORM: "طور", TAG: "NOUN"},
-            {ORTH: "ه", LEMMA: "ه", NORM: "ه", TAG: "VERB"},
-        ],
-        "عاشوراست": [
-            {ORTH: "عاشورا", LEMMA: "عاشورا", NORM: "عاشورا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "عبارتند": [
-            {ORTH: "عبارت", LEMMA: "عبارت", NORM: "عبارت", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "عزیزانتان": [
-            {ORTH: "عزیزان", LEMMA: "عزیزان", NORM: "عزیزان", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "عزیزانش": [
-            {ORTH: "عزیزان", LEMMA: "عزیزان", NORM: "عزیزان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "عزیزش": [
-            {ORTH: "عزیز", LEMMA: "عزیز", NORM: "عزیز", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "عشرت‌طلبی‌اش": [
-            {ORTH: "عشرت‌طلبی‌", LEMMA: "عشرت‌طلبی‌", NORM: "عشرت‌طلبی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "عقبیم": [
-            {ORTH: "عقب", LEMMA: "عقب", NORM: "عقب", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "علاقه‌اش": [
-            {ORTH: "علاقه‌", LEMMA: "علاقه‌", NORM: "علاقه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "علمیمان": [
-            {ORTH: "علمی", LEMMA: "علمی", NORM: "علمی", TAG: "ADJ"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "عمرش": [
-            {ORTH: "عمر", LEMMA: "عمر", NORM: "عمر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "عمرشان": [
-            {ORTH: "عمر", LEMMA: "عمر", NORM: "عمر", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "عملش": [
-            {ORTH: "عمل", LEMMA: "عمل", NORM: "عمل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "عملی‌اند": [
-            {ORTH: "عملی‌", LEMMA: "عملی‌", NORM: "عملی‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "عمویت": [
-            {ORTH: "عموی", LEMMA: "عموی", NORM: "عموی", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "عمویش": [
-            {ORTH: "عموی", LEMMA: "عموی", NORM: "عموی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "عمیقش": [
-            {ORTH: "عمیق", LEMMA: "عمیق", NORM: "عمیق", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "عواملش": [
-            {ORTH: "عوامل", LEMMA: "عوامل", NORM: "عوامل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "عوضشان": [
-            {ORTH: "عوض", LEMMA: "عوض", NORM: "عوض", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "غذایی‌شان": [
-            {ORTH: "غذایی‌", LEMMA: "غذایی‌", NORM: "غذایی‌", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "غریبه‌اند": [
-            {ORTH: "غریبه‌", LEMMA: "غریبه‌", NORM: "غریبه‌", TAG: "NOUN"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "غلامانش": [
-            {ORTH: "غلامان", LEMMA: "غلامان", NORM: "غلامان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "غلطهاست": [
-            {ORTH: "غلطها", LEMMA: "غلطها", NORM: "غلطها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "فراموشتان": [
-            {ORTH: "فراموش", LEMMA: "فراموش", NORM: "فراموش", TAG: "ADJ"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "فردی‌اند": [
-            {ORTH: "فردی‌", LEMMA: "فردی‌", NORM: "فردی‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "فرزندانش": [
-            {ORTH: "فرزندان", LEMMA: "فرزندان", NORM: "فرزندان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "فرزندش": [
-            {ORTH: "فرزند", LEMMA: "فرزند", NORM: "فرزند", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "فرم‌هایش": [
-            {ORTH: "فرم‌های", LEMMA: "فرم‌های", NORM: "فرم‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "فرهنگی‌مان": [
-            {ORTH: "فرهنگی‌", LEMMA: "فرهنگی‌", NORM: "فرهنگی‌", TAG: "ADJ"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "فریادشان": [
-            {ORTH: "فریاد", LEMMA: "فریاد", NORM: "فریاد", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "فضایی‌شان": [
-            {ORTH: "فضایی‌", LEMMA: "فضایی‌", NORM: "فضایی‌", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "فقیرشان": [
-            {ORTH: "فقیر", LEMMA: "فقیر", NORM: "فقیر", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "فوری‌شان": [
-            {ORTH: "فوری‌", LEMMA: "فوری‌", NORM: "فوری‌", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "قائلند": [
-            {ORTH: "قائل", LEMMA: "قائل", NORM: "قائل", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "قائلیم": [
-            {ORTH: "قائل", LEMMA: "قائل", NORM: "قائل", TAG: "ADJ"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "قادرند": [
-            {ORTH: "قادر", LEMMA: "قادر", NORM: "قادر", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "قانونمندش": [
-            {ORTH: "قانونمند", LEMMA: "قانونمند", NORM: "قانونمند", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "قبلند": [
-            {ORTH: "قبل", LEMMA: "قبل", NORM: "قبل", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "قبلی‌اش": [
-            {ORTH: "قبلی‌", LEMMA: "قبلی‌", NORM: "قبلی‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "قبلی‌مان": [
-            {ORTH: "قبلی‌", LEMMA: "قبلی‌", NORM: "قبلی‌", TAG: "ADJ"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "قدریست": [
-            {ORTH: "قدری", LEMMA: "قدری", NORM: "قدری", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "قدمش": [
-            {ORTH: "قدم", LEMMA: "قدم", NORM: "قدم", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "قسمتش": [
-            {ORTH: "قسمت", LEMMA: "قسمت", NORM: "قسمت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "قضایاست": [
-            {ORTH: "قضایا", LEMMA: "قضایا", NORM: "قضایا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "قضیه‌شان": [
-            {ORTH: "قضیه‌", LEMMA: "قضیه‌", NORM: "قضیه‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "قهرمانهایشان": [
-            {ORTH: "قهرمانهای", LEMMA: "قهرمانهای", NORM: "قهرمانهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "قهرمانیش": [
-            {ORTH: "قهرمانی", LEMMA: "قهرمانی", NORM: "قهرمانی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "قومت": [
-            {ORTH: "قوم", LEMMA: "قوم", NORM: "قوم", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "لازمه‌اش": [
-            {ORTH: "لازمه‌", LEMMA: "لازمه‌", NORM: "لازمه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "مأموریتش": [
-            {ORTH: "مأموریت", LEMMA: "مأموریت", NORM: "مأموریت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مأموریتم": [
-            {ORTH: "مأموریت", LEMMA: "مأموریت", NORM: "مأموریت", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "مأموریت‌اند": [
-            {ORTH: "مأموریت‌", LEMMA: "مأموریت‌", NORM: "مأموریت‌", TAG: "NOUN"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "مادرانشان": [
-            {ORTH: "مادران", LEMMA: "مادران", NORM: "مادران", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مادرت": [
-            {ORTH: "مادر", LEMMA: "مادر", NORM: "مادر", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "مادرش": [
-            {ORTH: "مادر", LEMMA: "مادر", NORM: "مادر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مادرم": [
-            {ORTH: "مادر", LEMMA: "مادر", NORM: "مادر", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "ماست": [
-            {ORTH: "ما", LEMMA: "ما", NORM: "ما", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "مالی‌اش": [
-            {ORTH: "مالی‌", LEMMA: "مالی‌", NORM: "مالی‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "ماهیتش": [
-            {ORTH: "ماهیت", LEMMA: "ماهیت", NORM: "ماهیت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مایی": [
-            {ORTH: "ما", LEMMA: "ما", NORM: "ما", TAG: "NOUN"},
-            {ORTH: "یی", LEMMA: "یی", NORM: "یی", TAG: "VERB"},
-        ],
-        "مجازاتش": [
-            {ORTH: "مجازات", LEMMA: "مجازات", NORM: "مجازات", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مجبورند": [
-            {ORTH: "مجبور", LEMMA: "مجبور", NORM: "مجبور", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "محتاجند": [
-            {ORTH: "محتاج", LEMMA: "محتاج", NORM: "محتاج", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "محرمم": [
-            {ORTH: "محرم", LEMMA: "محرم", NORM: "محرم", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "SCONJ"},
-        ],
-        "محلش": [
-            {ORTH: "محل", LEMMA: "محل", NORM: "محل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مخالفند": [
-            {ORTH: "مخالف", LEMMA: "مخالف", NORM: "مخالف", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مخدرش": [
-            {ORTH: "مخدر", LEMMA: "مخدر", NORM: "مخدر", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مدتهاست": [
-            {ORTH: "مدتها", LEMMA: "مدتها", NORM: "مدتها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "مدرسه‌ات": [
-            {ORTH: "مدرسه", LEMMA: "مدرسه", NORM: "مدرسه", TAG: "NOUN"},
-            {ORTH: "‌ات", LEMMA: "ات", NORM: "ات", TAG: "NOUN"},
-        ],
-        "مدرکم": [
-            {ORTH: "مدرک", LEMMA: "مدرک", NORM: "مدرک", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "مدیرانش": [
-            {ORTH: "مدیران", LEMMA: "مدیران", NORM: "مدیران", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مدیونم": [
-            {ORTH: "مدیون", LEMMA: "مدیون", NORM: "مدیون", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "مذهبی‌اند": [
-            {ORTH: "مذهبی‌", LEMMA: "مذهبی‌", NORM: "مذهبی‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "مرا": [
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-            {ORTH: "را", LEMMA: "را", NORM: "را", TAG: "PART"},
-        ],
-        "مرادت": [
-            {ORTH: "مراد", LEMMA: "مراد", NORM: "مراد", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "مردمشان": [
-            {ORTH: "مردم", LEMMA: "مردم", NORM: "مردم", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مردمند": [
-            {ORTH: "مردم", LEMMA: "مردم", NORM: "مردم", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مردم‌اند": [
-            {ORTH: "مردم‌", LEMMA: "مردم‌", NORM: "مردم‌", TAG: "NOUN"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "مرزشان": [
-            {ORTH: "مرز", LEMMA: "مرز", NORM: "مرز", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مرزهاشان": [
-            {ORTH: "مرزها", LEMMA: "مرزها", NORM: "مرزها", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مزدورش": [
-            {ORTH: "مزدور", LEMMA: "مزدور", NORM: "مزدور", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مسئولیتش": [
-            {ORTH: "مسئولیت", LEMMA: "مسئولیت", NORM: "مسئولیت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مسائلش": [
-            {ORTH: "مسائل", LEMMA: "مسائل", NORM: "مسائل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مستحضرید": [
-            {ORTH: "مستحضر", LEMMA: "مستحضر", NORM: "مستحضر", TAG: "ADJ"},
-            {ORTH: "ید", LEMMA: "ید", NORM: "ید", TAG: "VERB"},
-        ],
-        "مسلمانم": [
-            {ORTH: "مسلمان", LEMMA: "مسلمان", NORM: "مسلمان", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "مسلمانند": [
-            {ORTH: "مسلمان", LEMMA: "مسلمان", NORM: "مسلمان", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مشتریانش": [
-            {ORTH: "مشتریان", LEMMA: "مشتریان", NORM: "مشتریان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مشتهایمان": [
-            {ORTH: "مشتهای", LEMMA: "مشتهای", NORM: "مشتهای", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "مشخصند": [
-            {ORTH: "مشخص", LEMMA: "مشخص", NORM: "مشخص", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مشغولند": [
-            {ORTH: "مشغول", LEMMA: "مشغول", NORM: "مشغول", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مشغولیم": [
-            {ORTH: "مشغول", LEMMA: "مشغول", NORM: "مشغول", TAG: "ADJ"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "مشهورش": [
-            {ORTH: "مشهور", LEMMA: "مشهور", NORM: "مشهور", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مشکلاتشان": [
-            {ORTH: "مشکلات", LEMMA: "مشکلات", NORM: "مشکلات", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مشکلم": [
-            {ORTH: "مشکل", LEMMA: "مشکل", NORM: "مشکل", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "مطمئنم": [
-            {ORTH: "مطمئن", LEMMA: "مطمئن", NORM: "مطمئن", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "معامله‌مان": [
-            {ORTH: "معامله‌", LEMMA: "معامله‌", NORM: "معامله‌", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "معتقدم": [
-            {ORTH: "معتقد", LEMMA: "معتقد", NORM: "معتقد", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "معتقدند": [
-            {ORTH: "معتقد", LEMMA: "معتقد", NORM: "معتقد", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "معتقدیم": [
-            {ORTH: "معتقد", LEMMA: "معتقد", NORM: "معتقد", TAG: "ADJ"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "معرفی‌اش": [
-            {ORTH: "معرفی‌", LEMMA: "معرفی‌", NORM: "معرفی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "معروفش": [
-            {ORTH: "معروف", LEMMA: "معروف", NORM: "معروف", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "معضلاتمان": [
-            {ORTH: "معضلات", LEMMA: "معضلات", NORM: "معضلات", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "معلمش": [
-            {ORTH: "معلم", LEMMA: "معلم", NORM: "معلم", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "معنایش": [
-            {ORTH: "معنای", LEMMA: "معنای", NORM: "معنای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مغزشان": [
-            {ORTH: "مغز", LEMMA: "مغز", NORM: "مغز", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مفیدند": [
-            {ORTH: "مفید", LEMMA: "مفید", NORM: "مفید", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مقابلش": [
-            {ORTH: "مقابل", LEMMA: "مقابل", NORM: "مقابل", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مقاله‌اش": [
-            {ORTH: "مقاله‌", LEMMA: "مقاله‌", NORM: "مقاله‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "مقدمش": [
-            {ORTH: "مقدم", LEMMA: "مقدم", NORM: "مقدم", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مقرش": [
-            {ORTH: "مقر", LEMMA: "مقر", NORM: "مقر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مقصدشان": [
-            {ORTH: "مقصد", LEMMA: "مقصد", NORM: "مقصد", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مقصرند": [
-            {ORTH: "مقصر", LEMMA: "مقصر", NORM: "مقصر", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مقصودتان": [
-            {ORTH: "مقصود", LEMMA: "مقصود", NORM: "مقصود", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "ملاقاتهایش": [
-            {ORTH: "ملاقاتهای", LEMMA: "ملاقاتهای", NORM: "ملاقاتهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "ممکنشان": [
-            {ORTH: "ممکن", LEMMA: "ممکن", NORM: "ممکن", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "ممیزیهاست": [
-            {ORTH: "ممیزیها", LEMMA: "ممیزیها", NORM: "ممیزیها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "منظورم": [
-            {ORTH: "منظور", LEMMA: "منظور", NORM: "منظور", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "منی": [
-            {ORTH: "من", LEMMA: "من", NORM: "من", TAG: "NOUN"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "منید": [
-            {ORTH: "من", LEMMA: "من", NORM: "من", TAG: "NOUN"},
-            {ORTH: "ید", LEMMA: "ید", NORM: "ید", TAG: "VERB"},
-        ],
-        "مهربانش": [
-            {ORTH: "مهربان", LEMMA: "مهربان", NORM: "مهربان", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "مهم‌اند": [
-            {ORTH: "مهم‌", LEMMA: "مهم‌", NORM: "مهم‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "مواجهند": [
-            {ORTH: "مواجه", LEMMA: "مواجه", NORM: "مواجه", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "مواجه‌اند": [
-            {ORTH: "مواجه‌", LEMMA: "مواجه‌", NORM: "مواجه‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "مواخذه‌ات": [
-            {ORTH: "مواخذه", LEMMA: "مواخذه", NORM: "مواخذه", TAG: "NOUN"},
-            {ORTH: "‌ات", LEMMA: "ات", NORM: "ات", TAG: "NOUN"},
-        ],
-        "مواضعشان": [
-            {ORTH: "مواضع", LEMMA: "مواضع", NORM: "مواضع", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "مواضعمان": [
-            {ORTH: "مواضع", LEMMA: "مواضع", NORM: "مواضع", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "موافقند": [
-            {ORTH: "موافق", LEMMA: "موافق", NORM: "موافق", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "موجوداتش": [
-            {ORTH: "موجودات", LEMMA: "موجودات", NORM: "موجودات", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "موجودند": [
-            {ORTH: "موجود", LEMMA: "موجود", NORM: "موجود", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "موردش": [
-            {ORTH: "مورد", LEMMA: "مورد", NORM: "مورد", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "موضعشان": [
-            {ORTH: "موضع", LEMMA: "موضع", NORM: "موضع", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "موظفند": [
-            {ORTH: "موظف", LEMMA: "موظف", NORM: "موظف", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "موهایش": [
-            {ORTH: "موهای", LEMMA: "موهای", NORM: "موهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "موهایمان": [
-            {ORTH: "موهای", LEMMA: "موهای", NORM: "موهای", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "مویم": [
-            {ORTH: "مو", LEMMA: "مو", NORM: "مو", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "NOUN"},
-        ],
-        "ناخرسندند": [
-            {ORTH: "ناخرسند", LEMMA: "ناخرسند", NORM: "ناخرسند", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "ناراحتیش": [
-            {ORTH: "ناراحتی", LEMMA: "ناراحتی", NORM: "ناراحتی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "ناراضی‌اند": [
-            {ORTH: "ناراضی‌", LEMMA: "ناراضی‌", NORM: "ناراضی‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "نارواست": [
-            {ORTH: "ناروا", LEMMA: "ناروا", NORM: "ناروا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "نازش": [
-            {ORTH: "ناز", LEMMA: "ناز", NORM: "ناز", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "نامش": [
-            {ORTH: "نام", LEMMA: "نام", NORM: "نام", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "نامشان": [
-            {ORTH: "نام", LEMMA: "نام", NORM: "نام", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نامم": [
-            {ORTH: "نام", LEMMA: "نام", NORM: "نام", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "نامه‌ات": [
-            {ORTH: "نامه", LEMMA: "نامه", NORM: "نامه", TAG: "NOUN"},
-            {ORTH: "‌ات", LEMMA: "ات", NORM: "ات", TAG: "NOUN"},
-        ],
-        "نامه‌ام": [
-            {ORTH: "نامه‌", LEMMA: "نامه‌", NORM: "نامه‌", TAG: "NOUN"},
-            {ORTH: "ام", LEMMA: "ام", NORM: "ام", TAG: "NOUN"},
-        ],
-        "ناچارم": [
-            {ORTH: "ناچار", LEMMA: "ناچار", NORM: "ناچار", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "نخست‌وزیری‌اش": [
-            {
-                ORTH: "نخست‌وزیری‌",
-                LEMMA: "نخست‌وزیری‌",
-                NORM: "نخست‌وزیری‌",
-                TAG: "NOUN",
-            },
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "نزدش": [
-            {ORTH: "نزد", LEMMA: "نزد", NORM: "نزد", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "نشانم": [
-            {ORTH: "نشان", LEMMA: "نشان", NORM: "نشان", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "نظرات‌شان": [
-            {ORTH: "نظرات‌", LEMMA: "نظرات‌", NORM: "نظرات‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نظرتان": [
-            {ORTH: "نظر", LEMMA: "نظر", NORM: "نظر", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "نظرش": [
-            {ORTH: "نظر", LEMMA: "نظر", NORM: "نظر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "نظرشان": [
-            {ORTH: "نظر", LEMMA: "نظر", NORM: "نظر", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نظرم": [
-            {ORTH: "نظر", LEMMA: "نظر", NORM: "نظر", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "نظرهایشان": [
-            {ORTH: "نظرهای", LEMMA: "نظرهای", NORM: "نظرهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نفاقش": [
-            {ORTH: "نفاق", LEMMA: "نفاق", NORM: "نفاق", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "نفرند": [
-            {ORTH: "نفر", LEMMA: "نفر", NORM: "نفر", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "نفوذیند": [
-            {ORTH: "نفوذی", LEMMA: "نفوذی", NORM: "نفوذی", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "نقطه‌نظراتتان": [
-            {ORTH: "نقطه‌نظرات", LEMMA: "نقطه‌نظرات", NORM: "نقطه‌نظرات", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "نمایشی‌مان": [
-            {ORTH: "نمایشی‌", LEMMA: "نمایشی‌", NORM: "نمایشی‌", TAG: "ADJ"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "نمایندگی‌شان": [
-            {ORTH: "نمایندگی‌", LEMMA: "نمایندگی‌", NORM: "نمایندگی‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نمونه‌اش": [
-            {ORTH: "نمونه‌", LEMMA: "نمونه‌", NORM: "نمونه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "نمی‌پذیرندش": [
-            {ORTH: "نمی‌پذیرند", LEMMA: "نمی‌پذیرند", NORM: "نمی‌پذیرند", TAG: "VERB"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "نوآوری‌اش": [
-            {ORTH: "نوآوری‌", LEMMA: "نوآوری‌", NORM: "نوآوری‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "نوشته‌هایشان": [
-            {ORTH: "نوشته‌های", LEMMA: "نوشته‌های", NORM: "نوشته‌های", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نوشته‌هایم": [
-            {ORTH: "نوشته‌ها", LEMMA: "نوشته‌ها", NORM: "نوشته‌ها", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "NOUN"},
-        ],
-        "نکردنشان": [
-            {ORTH: "نکردن", LEMMA: "نکردن", NORM: "نکردن", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نگاهداری‌شان": [
-            {ORTH: "نگاهداری‌", LEMMA: "نگاهداری‌", NORM: "نگاهداری‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نگاهش": [
-            {ORTH: "نگاه", LEMMA: "نگاه", NORM: "نگاه", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "نگرانم": [
-            {ORTH: "نگران", LEMMA: "نگران", NORM: "نگران", TAG: "ADJ"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "VERB"},
-        ],
-        "نگرشهایشان": [
-            {ORTH: "نگرشهای", LEMMA: "نگرشهای", NORM: "نگرشهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "نیازمندند": [
-            {ORTH: "نیازمند", LEMMA: "نیازمند", NORM: "نیازمند", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "هدفش": [
-            {ORTH: "هدف", LEMMA: "هدف", NORM: "هدف", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "همانست": [
-            {ORTH: "همان", LEMMA: "همان", NORM: "همان", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "همراهش": [
-            {ORTH: "همراه", LEMMA: "همراه", NORM: "همراه", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "همسرتان": [
-            {ORTH: "همسر", LEMMA: "همسر", NORM: "همسر", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "همسرش": [
-            {ORTH: "همسر", LEMMA: "همسر", NORM: "همسر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "همسرم": [
-            {ORTH: "همسر", LEMMA: "همسر", NORM: "همسر", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "همفکرانش": [
-            {ORTH: "همفکران", LEMMA: "همفکران", NORM: "همفکران", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "همه‌اش": [
-            {ORTH: "همه‌", LEMMA: "همه‌", NORM: "همه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "همه‌شان": [
-            {ORTH: "همه‌", LEMMA: "همه‌", NORM: "همه‌", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "همکارانش": [
-            {ORTH: "همکاران", LEMMA: "همکاران", NORM: "همکاران", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "هم‌نظریم": [
-            {ORTH: "هم‌نظر", LEMMA: "هم‌نظر", NORM: "هم‌نظر", TAG: "ADJ"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "VERB"},
-        ],
-        "هنرش": [
-            {ORTH: "هنر", LEMMA: "هنر", NORM: "هنر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "هواست": [
-            {ORTH: "هوا", LEMMA: "هوا", NORM: "هوا", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "هویتش": [
-            {ORTH: "هویت", LEMMA: "هویت", NORM: "هویت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "وابسته‌اند": [
-            {ORTH: "وابسته‌", LEMMA: "وابسته‌", NORM: "وابسته‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "واقفند": [
-            {ORTH: "واقف", LEMMA: "واقف", NORM: "واقف", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "والدینشان": [
-            {ORTH: "والدین", LEMMA: "والدین", NORM: "والدین", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "وجدان‌تان": [
-            {ORTH: "وجدان‌", LEMMA: "وجدان‌", NORM: "وجدان‌", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "وجودشان": [
-            {ORTH: "وجود", LEMMA: "وجود", NORM: "وجود", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "وطنم": [
-            {ORTH: "وطن", LEMMA: "وطن", NORM: "وطن", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "وعده‌اش": [
-            {ORTH: "وعده‌", LEMMA: "وعده‌", NORM: "وعده‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "وقتمان": [
-            {ORTH: "وقت", LEMMA: "وقت", NORM: "وقت", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "ولادتش": [
-            {ORTH: "ولادت", LEMMA: "ولادت", NORM: "ولادت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پایانش": [
-            {ORTH: "پایان", LEMMA: "پایان", NORM: "پایان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پایش": [
-            {ORTH: "پای", LEMMA: "پای", NORM: "پای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پایین‌ترند": [
-            {ORTH: "پایین‌تر", LEMMA: "پایین‌تر", NORM: "پایین‌تر", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "پدرت": [
-            {ORTH: "پدر", LEMMA: "پدر", NORM: "پدر", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "پدرش": [
-            {ORTH: "پدر", LEMMA: "پدر", NORM: "پدر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پدرشان": [
-            {ORTH: "پدر", LEMMA: "پدر", NORM: "پدر", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "پدرم": [
-            {ORTH: "پدر", LEMMA: "پدر", NORM: "پدر", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "پربارش": [
-            {ORTH: "پربار", LEMMA: "پربار", NORM: "پربار", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پروردگارت": [
-            {ORTH: "پروردگار", LEMMA: "پروردگار", NORM: "پروردگار", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "پسرتان": [
-            {ORTH: "پسر", LEMMA: "پسر", NORM: "پسر", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "پسرش": [
-            {ORTH: "پسر", LEMMA: "پسر", NORM: "پسر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پسرعمویش": [
-            {ORTH: "پسرعموی", LEMMA: "پسرعموی", NORM: "پسرعموی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پسر‌عمویت": [
-            {ORTH: "پسر‌عموی", LEMMA: "پسر‌عموی", NORM: "پسر‌عموی", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "پشتش": [
-            {ORTH: "پشت", LEMMA: "پشت", NORM: "پشت", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پشیمونی": [
-            {ORTH: "پشیمون", LEMMA: "پشیمون", NORM: "پشیمون", TAG: "ADJ"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "پولش": [
-            {ORTH: "پول", LEMMA: "پول", NORM: "پول", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پژوهش‌هایش": [
-            {ORTH: "پژوهش‌های", LEMMA: "پژوهش‌های", NORM: "پژوهش‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پیامبرش": [
-            {ORTH: "پیامبر", LEMMA: "پیامبر", NORM: "پیامبر", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پیامبری": [
-            {ORTH: "پیامبر", LEMMA: "پیامبر", NORM: "پیامبر", TAG: "NOUN"},
-            {ORTH: "ی", LEMMA: "ی", NORM: "ی", TAG: "VERB"},
-        ],
-        "پیامش": [
-            {ORTH: "پیام", LEMMA: "پیام", NORM: "پیام", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پیداست": [
-            {ORTH: "پیدا", LEMMA: "پیدا", NORM: "پیدا", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "پیراهنش": [
-            {ORTH: "پیراهن", LEMMA: "پیراهن", NORM: "پیراهن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پیروانش": [
-            {ORTH: "پیروان", LEMMA: "پیروان", NORM: "پیروان", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "پیشانی‌اش": [
-            {ORTH: "پیشانی‌", LEMMA: "پیشانی‌", NORM: "پیشانی‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "پیمانت": [
-            {ORTH: "پیمان", LEMMA: "پیمان", NORM: "پیمان", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "پیوندشان": [
-            {ORTH: "پیوند", LEMMA: "پیوند", NORM: "پیوند", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "چاپش": [
-            {ORTH: "چاپ", LEMMA: "چاپ", NORM: "چاپ", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "چت": [
-            {ORTH: "چ", LEMMA: "چ", NORM: "چ", TAG: "ADV"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "چته": [
-            {ORTH: "چ", LEMMA: "چ", NORM: "چ", TAG: "ADV"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-            {ORTH: "ه", LEMMA: "ه", NORM: "ه", TAG: "VERB"},
-        ],
-        "چرخ‌هایش": [
-            {ORTH: "چرخ‌های", LEMMA: "چرخ‌های", NORM: "چرخ‌های", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "چشمم": [
-            {ORTH: "چشم", LEMMA: "چشم", NORM: "چشم", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "چشمهایش": [
-            {ORTH: "چشمهای", LEMMA: "چشمهای", NORM: "چشمهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "چشمهایشان": [
-            {ORTH: "چشمهای", LEMMA: "چشمهای", NORM: "چشمهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "چمنم": [
-            {ORTH: "چمن", LEMMA: "چمن", NORM: "چمن", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "چهره‌اش": [
-            {ORTH: "چهره‌", LEMMA: "چهره‌", NORM: "چهره‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "چکاره‌اند": [
-            {ORTH: "چکاره‌", LEMMA: "چکاره‌", NORM: "چکاره‌", TAG: "ADV"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "چیزهاست": [
-            {ORTH: "چیزها", LEMMA: "چیزها", NORM: "چیزها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "چیزهایش": [
-            {ORTH: "چیزهای", LEMMA: "چیزهای", NORM: "چیزهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "چیزیست": [
-            {ORTH: "چیزی", LEMMA: "چیزی", NORM: "چیزی", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "چیست": [
-            {ORTH: "چی", LEMMA: "چی", NORM: "چی", TAG: "ADV"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "کارش": [
-            {ORTH: "کار", LEMMA: "کار", NORM: "کار", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "کارشان": [
-            {ORTH: "کار", LEMMA: "کار", NORM: "کار", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "کارم": [
-            {ORTH: "کار", LEMMA: "کار", NORM: "کار", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "کارند": [
-            {ORTH: "کار", LEMMA: "کار", NORM: "کار", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "کارهایم": [
-            {ORTH: "کارها", LEMMA: "کارها", NORM: "کارها", TAG: "NOUN"},
-            {ORTH: "یم", LEMMA: "یم", NORM: "یم", TAG: "NOUN"},
-        ],
-        "کافیست": [
-            {ORTH: "کافی", LEMMA: "کافی", NORM: "کافی", TAG: "ADJ"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "کتابخانه‌اش": [
-            {ORTH: "کتابخانه‌", LEMMA: "کتابخانه‌", NORM: "کتابخانه‌", TAG: "NOUN"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "کتابش": [
-            {ORTH: "کتاب", LEMMA: "کتاب", NORM: "کتاب", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "کتابهاشان": [
-            {ORTH: "کتابها", LEMMA: "کتابها", NORM: "کتابها", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "کجاست": [
-            {ORTH: "کجا", LEMMA: "کجا", NORM: "کجا", TAG: "ADV"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "کدورتهایشان": [
-            {ORTH: "کدورتهای", LEMMA: "کدورتهای", NORM: "کدورتهای", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "کردنش": [
-            {ORTH: "کردن", LEMMA: "کردن", NORM: "کردن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "کرم‌خورده‌اش": [
-            {ORTH: "کرم‌خورده‌", LEMMA: "کرم‌خورده‌", NORM: "کرم‌خورده‌", TAG: "ADJ"},
-            {ORTH: "اش", LEMMA: "اش", NORM: "اش", TAG: "NOUN"},
-        ],
-        "کشش": [
-            {ORTH: "کش", LEMMA: "کش", NORM: "کش", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "کشورش": [
-            {ORTH: "کشور", LEMMA: "کشور", NORM: "کشور", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "کشورشان": [
-            {ORTH: "کشور", LEMMA: "کشور", NORM: "کشور", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "کشورمان": [
-            {ORTH: "کشور", LEMMA: "کشور", NORM: "کشور", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "کشورهاست": [
-            {ORTH: "کشورها", LEMMA: "کشورها", NORM: "کشورها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "کلیشه‌هاست": [
-            {ORTH: "کلیشه‌ها", LEMMA: "کلیشه‌ها", NORM: "کلیشه‌ها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "کمبودهاست": [
-            {ORTH: "کمبودها", LEMMA: "کمبودها", NORM: "کمبودها", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "کمتره": [
-            {ORTH: "کمتر", LEMMA: "کمتر", NORM: "کمتر", TAG: "ADJ"},
-            {ORTH: "ه", LEMMA: "ه", NORM: "ه", TAG: "VERB"},
-        ],
-        "کمکم": [
-            {ORTH: "کمک", LEMMA: "کمک", NORM: "کمک", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "کنارش": [
-            {ORTH: "کنار", LEMMA: "کنار", NORM: "کنار", TAG: "ADP"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "کودکانشان": [
-            {ORTH: "کودکان", LEMMA: "کودکان", NORM: "کودکان", TAG: "NOUN"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "کوچکش": [
-            {ORTH: "کوچک", LEMMA: "کوچک", NORM: "کوچک", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "کیست": [
-            {ORTH: "کی", LEMMA: "کی", NORM: "کی", TAG: "NOUN"},
-            {ORTH: "ست", LEMMA: "ست", NORM: "ست", TAG: "VERB"},
-        ],
-        "کیفش": [
-            {ORTH: "کیف", LEMMA: "کیف", NORM: "کیف", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گذشته‌اند": [
-            {ORTH: "گذشته‌", LEMMA: "گذشته‌", NORM: "گذشته‌", TAG: "ADJ"},
-            {ORTH: "اند", LEMMA: "اند", NORM: "اند", TAG: "VERB"},
-        ],
-        "گرانقدرش": [
-            {ORTH: "گرانقدر", LEMMA: "گرانقدر", NORM: "گرانقدر", TAG: "ADJ"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گرانقدرشان": [
-            {ORTH: "گرانقدر", LEMMA: "گرانقدر", NORM: "گرانقدر", TAG: "ADJ"},
-            {ORTH: "شان", LEMMA: "شان", NORM: "شان", TAG: "NOUN"},
-        ],
-        "گردنتان": [
-            {ORTH: "گردن", LEMMA: "گردن", NORM: "گردن", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "گردنش": [
-            {ORTH: "گردن", LEMMA: "گردن", NORM: "گردن", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گرفتارند": [
-            {ORTH: "گرفتار", LEMMA: "گرفتار", NORM: "گرفتار", TAG: "ADJ"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "گرفتنت": [
-            {ORTH: "گرفتن", LEMMA: "گرفتن", NORM: "گرفتن", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "گروهند": [
-            {ORTH: "گروه", LEMMA: "گروه", NORM: "گروه", TAG: "NOUN"},
-            {ORTH: "ند", LEMMA: "ند", NORM: "ند", TAG: "VERB"},
-        ],
-        "گروگانهایش": [
-            {ORTH: "گروگانهای", LEMMA: "گروگانهای", NORM: "گروگانهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گریمش": [
-            {ORTH: "گریم", LEMMA: "گریم", NORM: "گریم", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گفتارمان": [
-            {ORTH: "گفتار", LEMMA: "گفتار", NORM: "گفتار", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "گلهایش": [
-            {ORTH: "گلهای", LEMMA: "گلهای", NORM: "گلهای", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گلویش": [
-            {ORTH: "گلوی", LEMMA: "گلوی", NORM: "گلوی", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گناهت": [
-            {ORTH: "گناه", LEMMA: "گناه", NORM: "گناه", TAG: "NOUN"},
-            {ORTH: "ت", LEMMA: "ت", NORM: "ت", TAG: "NOUN"},
-        ],
-        "گوشش": [
-            {ORTH: "گوش", LEMMA: "گوش", NORM: "گوش", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "گوشم": [
-            {ORTH: "گوش", LEMMA: "گوش", NORM: "گوش", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "گولش": [
-            {ORTH: "گول", LEMMA: "گول", NORM: "گول", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-        "یادتان": [
-            {ORTH: "یاد", LEMMA: "یاد", NORM: "یاد", TAG: "NOUN"},
-            {ORTH: "تان", LEMMA: "تان", NORM: "تان", TAG: "NOUN"},
-        ],
-        "یادم": [
-            {ORTH: "یاد", LEMMA: "یاد", NORM: "یاد", TAG: "NOUN"},
-            {ORTH: "م", LEMMA: "م", NORM: "م", TAG: "NOUN"},
-        ],
-        "یادمان": [
-            {ORTH: "یاد", LEMMA: "یاد", NORM: "یاد", TAG: "NOUN"},
-            {ORTH: "مان", LEMMA: "مان", NORM: "مان", TAG: "NOUN"},
-        ],
-        "یارانش": [
-            {ORTH: "یاران", LEMMA: "یاران", NORM: "یاران", TAG: "NOUN"},
-            {ORTH: "ش", LEMMA: "ش", NORM: "ش", TAG: "NOUN"},
-        ],
-    }
-)
-TOKENIZER_EXCEPTIONS = _exc
diff --git a/spacy/lang/fi/tokenizer_exceptions.py b/spacy/lang/fi/tokenizer_exceptions.py
index faaf609f9..22d710cb0 100644
--- a/spacy/lang/fi/tokenizer_exceptions.py
+++ b/spacy/lang/fi/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH
 from ...util import update_exc
 
 
@@ -8,74 +8,74 @@ _exc = {}
 
 # Source https://www.cs.tut.fi/~jkorpela/kielenopas/5.5.html
 for exc_data in [
-    {ORTH: "aik.", LEMMA: "aikaisempi"},
-    {ORTH: "alk.", LEMMA: "alkaen"},
-    {ORTH: "alv.", LEMMA: "arvonlisävero"},
-    {ORTH: "ark.", LEMMA: "arkisin"},
-    {ORTH: "as.", LEMMA: "asunto"},
-    {ORTH: "eaa.", LEMMA: "ennen ajanlaskun alkua"},
-    {ORTH: "ed.", LEMMA: "edellinen"},
-    {ORTH: "esim.", LEMMA: "esimerkki"},
-    {ORTH: "huom.", LEMMA: "huomautus"},
-    {ORTH: "jne.", LEMMA: "ja niin edelleen"},
-    {ORTH: "joht.", LEMMA: "johtaja"},
-    {ORTH: "k.", LEMMA: "kuollut"},
-    {ORTH: "ks.", LEMMA: "katso"},
-    {ORTH: "lk.", LEMMA: "luokka"},
-    {ORTH: "lkm.", LEMMA: "lukumäärä"},
-    {ORTH: "lyh.", LEMMA: "lyhenne"},
-    {ORTH: "läh.", LEMMA: "lähettäjä"},
-    {ORTH: "miel.", LEMMA: "mieluummin"},
-    {ORTH: "milj.", LEMMA: "miljoona"},
-    {ORTH: "Mm.", LEMMA: "muun muassa"},
-    {ORTH: "mm.", LEMMA: "muun muassa"},
-    {ORTH: "myöh.", LEMMA: "myöhempi"},
-    {ORTH: "n.", LEMMA: "noin"},
-    {ORTH: "nimim.", LEMMA: "nimimerkki"},
-    {ORTH: "n:o", LEMMA: "numero"},
-    {ORTH: "N:o", LEMMA: "numero"},
-    {ORTH: "nro", LEMMA: "numero"},
-    {ORTH: "ns.", LEMMA: "niin sanottu"},
-    {ORTH: "nyk.", LEMMA: "nykyinen"},
-    {ORTH: "oik.", LEMMA: "oikealla"},
-    {ORTH: "os.", LEMMA: "osoite"},
-    {ORTH: "p.", LEMMA: "päivä"},
-    {ORTH: "par.", LEMMA: "paremmin"},
-    {ORTH: "per.", LEMMA: "perustettu"},
-    {ORTH: "pj.", LEMMA: "puheenjohtaja"},
-    {ORTH: "puh.joht.", LEMMA: "puheenjohtaja"},
-    {ORTH: "prof.", LEMMA: "professori"},
-    {ORTH: "puh.", LEMMA: "puhelin"},
-    {ORTH: "pvm.", LEMMA: "päivämäärä"},
-    {ORTH: "rak.", LEMMA: "rakennettu"},
-    {ORTH: "ry.", LEMMA: "rekisteröity yhdistys"},
-    {ORTH: "s.", LEMMA: "sivu"},
-    {ORTH: "siht.", LEMMA: "sihteeri"},
-    {ORTH: "synt.", LEMMA: "syntynyt"},
-    {ORTH: "t.", LEMMA: "toivoo"},
-    {ORTH: "tark.", LEMMA: "tarkastanut"},
-    {ORTH: "til.", LEMMA: "tilattu"},
-    {ORTH: "tms.", LEMMA: "tai muuta sellaista"},
-    {ORTH: "toim.", LEMMA: "toimittanut"},
-    {ORTH: "v.", LEMMA: "vuosi"},
-    {ORTH: "vas.", LEMMA: "vasen"},
-    {ORTH: "vast.", LEMMA: "vastaus"},
-    {ORTH: "vrt.", LEMMA: "vertaa"},
-    {ORTH: "yht.", LEMMA: "yhteensä"},
-    {ORTH: "yl.", LEMMA: "yleinen"},
-    {ORTH: "ym.", LEMMA: "ynnä muuta"},
-    {ORTH: "yms.", LEMMA: "ynnä muuta sellaista"},
-    {ORTH: "yo.", LEMMA: "ylioppilas"},
-    {ORTH: "yliopp.", LEMMA: "ylioppilas"},
-    {ORTH: "ao.", LEMMA: "asianomainen"},
-    {ORTH: "em.", LEMMA: "edellä mainittu"},
-    {ORTH: "ko.", LEMMA: "kyseessä oleva"},
-    {ORTH: "ml.", LEMMA: "mukaan luettuna"},
-    {ORTH: "po.", LEMMA: "puheena oleva"},
-    {ORTH: "so.", LEMMA: "se on"},
-    {ORTH: "ts.", LEMMA: "toisin sanoen"},
-    {ORTH: "vm.", LEMMA: "viimeksi mainittu"},
-    {ORTH: "srk.", LEMMA: "seurakunta"},
+    {ORTH: "aik."},
+    {ORTH: "alk."},
+    {ORTH: "alv."},
+    {ORTH: "ark."},
+    {ORTH: "as."},
+    {ORTH: "eaa."},
+    {ORTH: "ed."},
+    {ORTH: "esim."},
+    {ORTH: "huom."},
+    {ORTH: "jne."},
+    {ORTH: "joht."},
+    {ORTH: "k."},
+    {ORTH: "ks."},
+    {ORTH: "lk."},
+    {ORTH: "lkm."},
+    {ORTH: "lyh."},
+    {ORTH: "läh."},
+    {ORTH: "miel."},
+    {ORTH: "milj."},
+    {ORTH: "Mm."},
+    {ORTH: "mm."},
+    {ORTH: "myöh."},
+    {ORTH: "n."},
+    {ORTH: "nimim."},
+    {ORTH: "n:o"},
+    {ORTH: "N:o"},
+    {ORTH: "nro"},
+    {ORTH: "ns."},
+    {ORTH: "nyk."},
+    {ORTH: "oik."},
+    {ORTH: "os."},
+    {ORTH: "p."},
+    {ORTH: "par."},
+    {ORTH: "per."},
+    {ORTH: "pj."},
+    {ORTH: "puh.joht."},
+    {ORTH: "prof."},
+    {ORTH: "puh."},
+    {ORTH: "pvm."},
+    {ORTH: "rak."},
+    {ORTH: "ry."},
+    {ORTH: "s."},
+    {ORTH: "siht."},
+    {ORTH: "synt."},
+    {ORTH: "t."},
+    {ORTH: "tark."},
+    {ORTH: "til."},
+    {ORTH: "tms."},
+    {ORTH: "toim."},
+    {ORTH: "v."},
+    {ORTH: "vas."},
+    {ORTH: "vast."},
+    {ORTH: "vrt."},
+    {ORTH: "yht."},
+    {ORTH: "yl."},
+    {ORTH: "ym."},
+    {ORTH: "yms."},
+    {ORTH: "yo."},
+    {ORTH: "yliopp."},
+    {ORTH: "ao."},
+    {ORTH: "em."},
+    {ORTH: "ko."},
+    {ORTH: "ml."},
+    {ORTH: "po."},
+    {ORTH: "so."},
+    {ORTH: "ts."},
+    {ORTH: "vm."},
+    {ORTH: "srk."},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/fr/tokenizer_exceptions.py b/spacy/lang/fr/tokenizer_exceptions.py
index a1ad7bcbb..6f429eecc 100644
--- a/spacy/lang/fr/tokenizer_exceptions.py
+++ b/spacy/lang/fr/tokenizer_exceptions.py
@@ -3,7 +3,7 @@ import re
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
 from .punctuation import ELISION, HYPHENS
 from ..char_classes import ALPHA_LOWER, ALPHA
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH
 from ...util import update_exc
 
 
@@ -28,29 +28,29 @@ def lower_first_letter(text):
     return text[0].lower() + text[1:]
 
 
-_exc = {"J.-C.": [{LEMMA: "Jésus", ORTH: "J."}, {LEMMA: "Christ", ORTH: "-C."}]}
+_exc = {"J.-C.": [{ORTH: "J."}, {ORTH: "-C."}]}
 
 
 for exc_data in [
-    {LEMMA: "avant", ORTH: "av."},
-    {LEMMA: "janvier", ORTH: "janv."},
-    {LEMMA: "février", ORTH: "févr."},
-    {LEMMA: "avril", ORTH: "avr."},
-    {LEMMA: "juillet", ORTH: "juill."},
-    {LEMMA: "septembre", ORTH: "sept."},
-    {LEMMA: "octobre", ORTH: "oct."},
-    {LEMMA: "novembre", ORTH: "nov."},
-    {LEMMA: "décembre", ORTH: "déc."},
-    {LEMMA: "après", ORTH: "apr."},
-    {LEMMA: "docteur", ORTH: "Dr."},
-    {LEMMA: "monsieur", ORTH: "M."},
-    {LEMMA: "monsieur", ORTH: "Mr."},
-    {LEMMA: "madame", ORTH: "Mme."},
-    {LEMMA: "mademoiselle", ORTH: "Mlle."},
-    {LEMMA: "numéro", ORTH: "n°"},
-    {LEMMA: "degrés", ORTH: "d°"},
-    {LEMMA: "saint", ORTH: "St."},
-    {LEMMA: "sainte", ORTH: "Ste."},
+    {ORTH: "av."},
+    {ORTH: "janv."},
+    {ORTH: "févr."},
+    {ORTH: "avr."},
+    {ORTH: "juill."},
+    {ORTH: "sept."},
+    {ORTH: "oct."},
+    {ORTH: "nov."},
+    {ORTH: "déc."},
+    {ORTH: "apr."},
+    {ORTH: "Dr."},
+    {ORTH: "M."},
+    {ORTH: "Mr."},
+    {ORTH: "Mme."},
+    {ORTH: "Mlle."},
+    {ORTH: "n°"},
+    {ORTH: "d°"},
+    {ORTH: "St."},
+    {ORTH: "Ste."},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
@@ -80,55 +80,37 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-for verb, verb_lemma in [
-    ("a", "avoir"),
-    ("est", "être"),
-    ("semble", "sembler"),
-    ("indique", "indiquer"),
-    ("moque", "moquer"),
-    ("passe", "passer"),
+for verb in [
+    "a",
+    "est" "semble",
+    "indique",
+    "moque",
+    "passe",
 ]:
     for orth in [verb, verb.title()]:
         for pronoun in ["elle", "il", "on"]:
             token = f"{orth}-t-{pronoun}"
-            _exc[token] = [
-                {LEMMA: verb_lemma, ORTH: orth},  # , TAG: "VERB"},
-                {LEMMA: "t", ORTH: "-t"},
-                {LEMMA: pronoun, ORTH: "-" + pronoun},
-            ]
+            _exc[token] = [{ORTH: orth}, {ORTH: "-t"}, {ORTH: "-" + pronoun}]
 
-for verb, verb_lemma in [("est", "être")]:
+for verb in ["est"]:
     for orth in [verb, verb.title()]:
-        token = f"{orth}-ce"
-        _exc[token] = [
-            {LEMMA: verb_lemma, ORTH: orth},  # , TAG: "VERB"},
-            {LEMMA: "ce", ORTH: "-ce"},
-        ]
+        _exc[f"{orth}-ce"] = [{ORTH: orth}, {ORTH: "-ce"}]
 
 
-for pre, pre_lemma in [("qu'", "que"), ("n'", "ne")]:
+for pre in ["qu'", "n'"]:
     for orth in [pre, pre.title()]:
-        _exc[f"{orth}est-ce"] = [
-            {LEMMA: pre_lemma, ORTH: orth},
-            {LEMMA: "être", ORTH: "est"},
-            {LEMMA: "ce", ORTH: "-ce"},
-        ]
+        _exc[f"{orth}est-ce"] = [{ORTH: orth}, {ORTH: "est"}, {ORTH: "-ce"}]
 
 
 for verb, pronoun in [("est", "il"), ("EST", "IL")]:
-    token = "{}-{}".format(verb, pronoun)
-    _exc[token] = [
-        {LEMMA: "être", ORTH: verb},
-        {LEMMA: pronoun, ORTH: "-" + pronoun},
-    ]
+    _exc[f"{verb}-{pronoun}"] = [{ORTH: verb}, {ORTH: "-" + pronoun}]
 
 
 for s, verb, pronoun in [("s", "est", "il"), ("S", "EST", "IL")]:
-    token = "{}'{}-{}".format(s, verb, pronoun)
-    _exc[token] = [
-        {LEMMA: "se", ORTH: s + "'"},
-        {LEMMA: "être", ORTH: verb},
-        {LEMMA: pronoun, ORTH: "-" + pronoun},
+    _exc[f"{s}'{verb}-{pronoun}"] = [
+        {ORTH: s + "'"},
+        {ORTH: verb},
+        {ORTH: "-" + pronoun},
     ]
 
 
diff --git a/spacy/lang/ga/tokenizer_exceptions.py b/spacy/lang/ga/tokenizer_exceptions.py
index fbd6fa0f5..abf49c511 100644
--- a/spacy/lang/ga/tokenizer_exceptions.py
+++ b/spacy/lang/ga/tokenizer_exceptions.py
@@ -1,81 +1,65 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import POS, DET, ADP, CCONJ, ADV, NOUN, X, AUX
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
 _exc = {
-    "'acha'n": [
-        {ORTH: "'ach", LEMMA: "gach", NORM: "gach", POS: DET},
-        {ORTH: "a'n", LEMMA: "aon", NORM: "aon", POS: DET},
-    ],
-    "dem'": [
-        {ORTH: "de", LEMMA: "de", NORM: "de", POS: ADP},
-        {ORTH: "m'", LEMMA: "mo", NORM: "mo", POS: DET},
-    ],
-    "ded'": [
-        {ORTH: "de", LEMMA: "de", NORM: "de", POS: ADP},
-        {ORTH: "d'", LEMMA: "do", NORM: "do", POS: DET},
-    ],
-    "lem'": [
-        {ORTH: "le", LEMMA: "le", NORM: "le", POS: ADP},
-        {ORTH: "m'", LEMMA: "mo", NORM: "mo", POS: DET},
-    ],
-    "led'": [
-        {ORTH: "le", LEMMA: "le", NORM: "le", POS: ADP},
-        {ORTH: "d'", LEMMA: "mo", NORM: "do", POS: DET},
-    ],
+    "'acha'n": [{ORTH: "'ach", NORM: "gach"}, {ORTH: "a'n", NORM: "aon"}],
+    "dem'": [{ORTH: "de", NORM: "de"}, {ORTH: "m'", NORM: "mo"}],
+    "ded'": [{ORTH: "de", NORM: "de"}, {ORTH: "d'", NORM: "do"}],
+    "lem'": [{ORTH: "le", NORM: "le"}, {ORTH: "m'", NORM: "mo"}],
+    "led'": [{ORTH: "le", NORM: "le"}, {ORTH: "d'", NORM: "do"}],
 }
 
 for exc_data in [
-    {ORTH: "'gus", LEMMA: "agus", NORM: "agus", POS: CCONJ},
-    {ORTH: "'ach", LEMMA: "gach", NORM: "gach", POS: DET},
-    {ORTH: "ao'", LEMMA: "aon", NORM: "aon"},
-    {ORTH: "'niar", LEMMA: "aniar", NORM: "aniar", POS: ADV},
-    {ORTH: "'níos", LEMMA: "aníos", NORM: "aníos", POS: ADV},
-    {ORTH: "'ndiu", LEMMA: "inniu", NORM: "inniu", POS: ADV},
-    {ORTH: "'nocht", LEMMA: "anocht", NORM: "anocht", POS: ADV},
-    {ORTH: "m'", LEMMA: "mo", POS: DET},
-    {ORTH: "Aib.", LEMMA: "Aibreán", POS: NOUN},
-    {ORTH: "Ath.", LEMMA: "athair", POS: NOUN},
-    {ORTH: "Beal.", LEMMA: "Bealtaine", POS: NOUN},
-    {ORTH: "a.C.n.", LEMMA: "ante Christum natum", POS: X},
-    {ORTH: "m.sh.", LEMMA: "mar shampla", POS: ADV},
-    {ORTH: "M.F.", LEMMA: "Meán Fómhair", POS: NOUN},
-    {ORTH: "M.Fómh.", LEMMA: "Meán Fómhair", POS: NOUN},
-    {ORTH: "D.F.", LEMMA: "Deireadh Fómhair", POS: NOUN},
-    {ORTH: "D.Fómh.", LEMMA: "Deireadh Fómhair", POS: NOUN},
-    {ORTH: "r.C.", LEMMA: "roimh Chríost", POS: ADV},
-    {ORTH: "R.C.", LEMMA: "roimh Chríost", POS: ADV},
-    {ORTH: "r.Ch.", LEMMA: "roimh Chríost", POS: ADV},
-    {ORTH: "r.Chr.", LEMMA: "roimh Chríost", POS: ADV},
-    {ORTH: "R.Ch.", LEMMA: "roimh Chríost", POS: ADV},
-    {ORTH: "R.Chr.", LEMMA: "roimh Chríost", POS: ADV},
-    {ORTH: "⁊rl.", LEMMA: "agus araile", POS: ADV},
-    {ORTH: "srl.", LEMMA: "agus araile", POS: ADV},
-    {ORTH: "Co.", LEMMA: "contae", POS: NOUN},
-    {ORTH: "Ean.", LEMMA: "Eanáir", POS: NOUN},
-    {ORTH: "Feab.", LEMMA: "Feabhra", POS: NOUN},
-    {ORTH: "gCo.", LEMMA: "contae", POS: NOUN},
-    {ORTH: ".i.", LEMMA: "eadhon", POS: ADV},
-    {ORTH: "B'", LEMMA: "ba", POS: AUX},
-    {ORTH: "b'", LEMMA: "ba", POS: AUX},
-    {ORTH: "lch.", LEMMA: "leathanach", POS: NOUN},
-    {ORTH: "Lch.", LEMMA: "leathanach", POS: NOUN},
-    {ORTH: "lgh.", LEMMA: "leathanach", POS: NOUN},
-    {ORTH: "Lgh.", LEMMA: "leathanach", POS: NOUN},
-    {ORTH: "Lún.", LEMMA: "Lúnasa", POS: NOUN},
-    {ORTH: "Már.", LEMMA: "Márta", POS: NOUN},
-    {ORTH: "Meith.", LEMMA: "Meitheamh", POS: NOUN},
-    {ORTH: "Noll.", LEMMA: "Nollaig", POS: NOUN},
-    {ORTH: "Samh.", LEMMA: "Samhain", POS: NOUN},
-    {ORTH: "tAth.", LEMMA: "athair", POS: NOUN},
-    {ORTH: "tUas.", LEMMA: "Uasal", POS: NOUN},
-    {ORTH: "teo.", LEMMA: "teoranta", POS: NOUN},
-    {ORTH: "Teo.", LEMMA: "teoranta", POS: NOUN},
-    {ORTH: "Uas.", LEMMA: "Uasal", POS: NOUN},
-    {ORTH: "uimh.", LEMMA: "uimhir", POS: NOUN},
-    {ORTH: "Uimh.", LEMMA: "uimhir", POS: NOUN},
+    {ORTH: "'gus", NORM: "agus"},
+    {ORTH: "'ach", NORM: "gach"},
+    {ORTH: "ao'", NORM: "aon"},
+    {ORTH: "'niar", NORM: "aniar"},
+    {ORTH: "'níos", NORM: "aníos"},
+    {ORTH: "'ndiu", NORM: "inniu"},
+    {ORTH: "'nocht", NORM: "anocht"},
+    {ORTH: "m'"},
+    {ORTH: "Aib."},
+    {ORTH: "Ath."},
+    {ORTH: "Beal."},
+    {ORTH: "a.C.n."},
+    {ORTH: "m.sh."},
+    {ORTH: "M.F."},
+    {ORTH: "M.Fómh."},
+    {ORTH: "D.F."},
+    {ORTH: "D.Fómh."},
+    {ORTH: "r.C."},
+    {ORTH: "R.C."},
+    {ORTH: "r.Ch."},
+    {ORTH: "r.Chr."},
+    {ORTH: "R.Ch."},
+    {ORTH: "R.Chr."},
+    {ORTH: "⁊rl."},
+    {ORTH: "srl."},
+    {ORTH: "Co."},
+    {ORTH: "Ean."},
+    {ORTH: "Feab."},
+    {ORTH: "gCo."},
+    {ORTH: ".i."},
+    {ORTH: "B'"},
+    {ORTH: "b'"},
+    {ORTH: "lch."},
+    {ORTH: "Lch."},
+    {ORTH: "lgh."},
+    {ORTH: "Lgh."},
+    {ORTH: "Lún."},
+    {ORTH: "Már."},
+    {ORTH: "Meith."},
+    {ORTH: "Noll."},
+    {ORTH: "Samh."},
+    {ORTH: "tAth."},
+    {ORTH: "tUas."},
+    {ORTH: "teo."},
+    {ORTH: "Teo."},
+    {ORTH: "Uas."},
+    {ORTH: "uimh."},
+    {ORTH: "Uimh."},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/id/tokenizer_exceptions.py b/spacy/lang/id/tokenizer_exceptions.py
index 50ccfa33a..ff77ede9f 100644
--- a/spacy/lang/id/tokenizer_exceptions.py
+++ b/spacy/lang/id/tokenizer_exceptions.py
@@ -1,6 +1,6 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
 from ._tokenizer_exceptions_list import ID_BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -11,53 +11,47 @@ _exc = {}
 
 for orth in ID_BASE_EXCEPTIONS:
     _exc[orth] = [{ORTH: orth}]
-
     orth_title = orth.title()
     _exc[orth_title] = [{ORTH: orth_title}]
-
     orth_caps = orth.upper()
     _exc[orth_caps] = [{ORTH: orth_caps}]
-
     orth_lower = orth.lower()
     _exc[orth_lower] = [{ORTH: orth_lower}]
-
     orth_first_upper = orth[0].upper() + orth[1:]
     _exc[orth_first_upper] = [{ORTH: orth_first_upper}]
-
     if "-" in orth:
         orth_title = "-".join([part.title() for part in orth.split("-")])
         _exc[orth_title] = [{ORTH: orth_title}]
-
         orth_caps = "-".join([part.upper() for part in orth.split("-")])
         _exc[orth_caps] = [{ORTH: orth_caps}]
 
 for exc_data in [
-    {ORTH: "Jan.", LEMMA: "Januari", NORM: "Januari"},
-    {ORTH: "Feb.", LEMMA: "Februari", NORM: "Februari"},
-    {ORTH: "Mar.", LEMMA: "Maret", NORM: "Maret"},
-    {ORTH: "Apr.", LEMMA: "April", NORM: "April"},
-    {ORTH: "Jun.", LEMMA: "Juni", NORM: "Juni"},
-    {ORTH: "Jul.", LEMMA: "Juli", NORM: "Juli"},
-    {ORTH: "Agu.", LEMMA: "Agustus", NORM: "Agustus"},
-    {ORTH: "Ags.", LEMMA: "Agustus", NORM: "Agustus"},
-    {ORTH: "Sep.", LEMMA: "September", NORM: "September"},
-    {ORTH: "Okt.", LEMMA: "Oktober", NORM: "Oktober"},
-    {ORTH: "Nov.", LEMMA: "November", NORM: "November"},
-    {ORTH: "Des.", LEMMA: "Desember", NORM: "Desember"},
+    {ORTH: "Jan.", NORM: "Januari"},
+    {ORTH: "Feb.", NORM: "Februari"},
+    {ORTH: "Mar.", NORM: "Maret"},
+    {ORTH: "Apr.", NORM: "April"},
+    {ORTH: "Jun.", NORM: "Juni"},
+    {ORTH: "Jul.", NORM: "Juli"},
+    {ORTH: "Agu.", NORM: "Agustus"},
+    {ORTH: "Ags.", NORM: "Agustus"},
+    {ORTH: "Sep.", NORM: "September"},
+    {ORTH: "Okt.", NORM: "Oktober"},
+    {ORTH: "Nov.", NORM: "November"},
+    {ORTH: "Des.", NORM: "Desember"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
 _other_exc = {
-    "do'a": [{ORTH: "do'a", LEMMA: "doa", NORM: "doa"}],
-    "jum'at": [{ORTH: "jum'at", LEMMA: "Jumat", NORM: "Jumat"}],
-    "Jum'at": [{ORTH: "Jum'at", LEMMA: "Jumat", NORM: "Jumat"}],
-    "la'nat": [{ORTH: "la'nat", LEMMA: "laknat", NORM: "laknat"}],
-    "ma'af": [{ORTH: "ma'af", LEMMA: "maaf", NORM: "maaf"}],
-    "mu'jizat": [{ORTH: "mu'jizat", LEMMA: "mukjizat", NORM: "mukjizat"}],
-    "Mu'jizat": [{ORTH: "Mu'jizat", LEMMA: "mukjizat", NORM: "mukjizat"}],
-    "ni'mat": [{ORTH: "ni'mat", LEMMA: "nikmat", NORM: "nikmat"}],
-    "raka'at": [{ORTH: "raka'at", LEMMA: "rakaat", NORM: "rakaat"}],
-    "ta'at": [{ORTH: "ta'at", LEMMA: "taat", NORM: "taat"}],
+    "do'a": [{ORTH: "do'a", NORM: "doa"}],
+    "jum'at": [{ORTH: "jum'at", NORM: "Jumat"}],
+    "Jum'at": [{ORTH: "Jum'at", NORM: "Jumat"}],
+    "la'nat": [{ORTH: "la'nat", NORM: "laknat"}],
+    "ma'af": [{ORTH: "ma'af", NORM: "maaf"}],
+    "mu'jizat": [{ORTH: "mu'jizat", NORM: "mukjizat"}],
+    "Mu'jizat": [{ORTH: "Mu'jizat", NORM: "mukjizat"}],
+    "ni'mat": [{ORTH: "ni'mat", NORM: "nikmat"}],
+    "raka'at": [{ORTH: "raka'at", NORM: "rakaat"}],
+    "ta'at": [{ORTH: "ta'at", NORM: "taat"}],
 }
 
 _exc.update(_other_exc)
diff --git a/spacy/lang/it/tokenizer_exceptions.py b/spacy/lang/it/tokenizer_exceptions.py
index c9c729d63..0c9968bc6 100644
--- a/spacy/lang/it/tokenizer_exceptions.py
+++ b/spacy/lang/it/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH
 from ...util import update_exc
 
 
@@ -10,7 +10,7 @@ _exc = {
     "L'art.": [{ORTH: "L'"}, {ORTH: "art."}],
     "l'art.": [{ORTH: "l'"}, {ORTH: "art."}],
     "nell'art.": [{ORTH: "nell'"}, {ORTH: "art."}],
-    "po'": [{ORTH: "po'", LEMMA: "poco"}],
+    "po'": [{ORTH: "po'"}],
     "sett..": [{ORTH: "sett."}, {ORTH: "."}],
 }
 
diff --git a/spacy/lang/lb/tokenizer_exceptions.py b/spacy/lang/lb/tokenizer_exceptions.py
index f6cdc7f34..d00dc9610 100644
--- a/spacy/lang/lb/tokenizer_exceptions.py
+++ b/spacy/lang/lb/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -10,19 +10,19 @@ _exc = {}
 
 # translate / delete what is not necessary
 for exc_data in [
-    {ORTH: "’t", LEMMA: "et", NORM: "et"},
-    {ORTH: "’T", LEMMA: "et", NORM: "et"},
-    {ORTH: "'t", LEMMA: "et", NORM: "et"},
-    {ORTH: "'T", LEMMA: "et", NORM: "et"},
-    {ORTH: "wgl.", LEMMA: "wannechgelift", NORM: "wannechgelift"},
-    {ORTH: "M.", LEMMA: "Monsieur", NORM: "Monsieur"},
-    {ORTH: "Mme.", LEMMA: "Madame", NORM: "Madame"},
-    {ORTH: "Dr.", LEMMA: "Dokter", NORM: "Dokter"},
-    {ORTH: "Tel.", LEMMA: "Telefon", NORM: "Telefon"},
-    {ORTH: "asw.", LEMMA: "an sou weider", NORM: "an sou weider"},
-    {ORTH: "etc.", LEMMA: "et cetera", NORM: "et cetera"},
-    {ORTH: "bzw.", LEMMA: "bezéiungsweis", NORM: "bezéiungsweis"},
-    {ORTH: "Jan.", LEMMA: "Januar", NORM: "Januar"},
+    {ORTH: "’t", NORM: "et"},
+    {ORTH: "’T", NORM: "et"},
+    {ORTH: "'t", NORM: "et"},
+    {ORTH: "'T", NORM: "et"},
+    {ORTH: "wgl.", NORM: "wannechgelift"},
+    {ORTH: "M.", NORM: "Monsieur"},
+    {ORTH: "Mme.", NORM: "Madame"},
+    {ORTH: "Dr.", NORM: "Dokter"},
+    {ORTH: "Tel.", NORM: "Telefon"},
+    {ORTH: "asw.", NORM: "an sou weider"},
+    {ORTH: "etc.", NORM: "et cetera"},
+    {ORTH: "bzw.", NORM: "bezéiungsweis"},
+    {ORTH: "Jan.", NORM: "Januar"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/lij/tokenizer_exceptions.py b/spacy/lang/lij/tokenizer_exceptions.py
index 61fa0df52..52eae2c89 100644
--- a/spacy/lang/lij/tokenizer_exceptions.py
+++ b/spacy/lang/lij/tokenizer_exceptions.py
@@ -1,53 +1,50 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH
 from ...util import update_exc
 
 
 _exc = {}
 
-for raw, lemma in [
-    ("a-a", "a-o"),
-    ("a-e", "a-o"),
-    ("a-o", "a-o"),
-    ("a-i", "a-o"),
-    ("co-a", "co-o"),
-    ("co-e", "co-o"),
-    ("co-i", "co-o"),
-    ("co-o", "co-o"),
-    ("da-a", "da-o"),
-    ("da-e", "da-o"),
-    ("da-i", "da-o"),
-    ("da-o", "da-o"),
-    ("pe-a", "pe-o"),
-    ("pe-e", "pe-o"),
-    ("pe-i", "pe-o"),
-    ("pe-o", "pe-o"),
+for raw in [
+    "a-e",
+    "a-o",
+    "a-i",
+    "a-a",
+    "co-a",
+    "co-e",
+    "co-i",
+    "co-o",
+    "da-a",
+    "da-e",
+    "da-i",
+    "da-o",
+    "pe-a",
+    "pe-e",
+    "pe-i",
+    "pe-o",
 ]:
     for orth in [raw, raw.capitalize()]:
-        _exc[orth] = [{ORTH: orth, LEMMA: lemma}]
+        _exc[orth] = [{ORTH: orth}]
 
 # Prefix + prepositions with à (e.g. "sott'a-o")
 
-for prep, prep_lemma in [
-    ("a-a", "a-o"),
-    ("a-e", "a-o"),
-    ("a-o", "a-o"),
-    ("a-i", "a-o"),
+for prep in [
+    "a-a",
+    "a-e",
+    "a-o",
+    "a-i",
 ]:
-    for prefix, prefix_lemma in [
-        ("sott'", "sotta"),
-        ("sott’", "sotta"),
-        ("contr'", "contra"),
-        ("contr’", "contra"),
-        ("ch'", "che"),
-        ("ch’", "che"),
-        ("s'", "se"),
-        ("s’", "se"),
+    for prefix in [
+        "sott'",
+        "sott’",
+        "contr'",
+        "contr’",
+        "ch'",
+        "ch’",
+        "s'",
+        "s’",
     ]:
         for prefix_orth in [prefix, prefix.capitalize()]:
-            _exc[prefix_orth + prep] = [
-                {ORTH: prefix_orth, LEMMA: prefix_lemma},
-                {ORTH: prep, LEMMA: prep_lemma},
-            ]
+            _exc[prefix_orth + prep] = [{ORTH: prefix_orth}, {ORTH: prep}]
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
diff --git a/spacy/lang/nb/tokenizer_exceptions.py b/spacy/lang/nb/tokenizer_exceptions.py
index 9a604cedc..0be436ae4 100644
--- a/spacy/lang/nb/tokenizer_exceptions.py
+++ b/spacy/lang/nb/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -7,17 +7,17 @@ _exc = {}
 
 
 for exc_data in [
-    {ORTH: "jan.", LEMMA: "januar"},
-    {ORTH: "feb.", LEMMA: "februar"},
-    {ORTH: "mar.", LEMMA: "mars"},
-    {ORTH: "apr.", LEMMA: "april"},
-    {ORTH: "jun.", LEMMA: "juni"},
-    {ORTH: "jul.", LEMMA: "juli"},
-    {ORTH: "aug.", LEMMA: "august"},
-    {ORTH: "sep.", LEMMA: "september"},
-    {ORTH: "okt.", LEMMA: "oktober"},
-    {ORTH: "nov.", LEMMA: "november"},
-    {ORTH: "des.", LEMMA: "desember"},
+    {ORTH: "jan.", NORM: "januar"},
+    {ORTH: "feb.", NORM: "februar"},
+    {ORTH: "mar.", NORM: "mars"},
+    {ORTH: "apr.", NORM: "april"},
+    {ORTH: "jun.", NORM: "juni"},
+    {ORTH: "jul.", NORM: "juli"},
+    {ORTH: "aug.", NORM: "august"},
+    {ORTH: "sep.", NORM: "september"},
+    {ORTH: "okt.", NORM: "oktober"},
+    {ORTH: "nov.", NORM: "november"},
+    {ORTH: "des.", NORM: "desember"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/ru/tokenizer_exceptions.py b/spacy/lang/ru/tokenizer_exceptions.py
index e4fbd2d75..1dc363fae 100644
--- a/spacy/lang/ru/tokenizer_exceptions.py
+++ b/spacy/lang/ru/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -7,58 +7,56 @@ _exc = {}
 
 _abbrev_exc = [
     # Weekdays abbreviations
-    {ORTH: "пн", LEMMA: "понедельник", NORM: "понедельник"},
-    {ORTH: "вт", LEMMA: "вторник", NORM: "вторник"},
-    {ORTH: "ср", LEMMA: "среда", NORM: "среда"},
-    {ORTH: "чт", LEMMA: "четверг", NORM: "четверг"},
-    {ORTH: "чтв", LEMMA: "четверг", NORM: "четверг"},
-    {ORTH: "пт", LEMMA: "пятница", NORM: "пятница"},
-    {ORTH: "сб", LEMMA: "суббота", NORM: "суббота"},
-    {ORTH: "сбт", LEMMA: "суббота", NORM: "суббота"},
-    {ORTH: "вс", LEMMA: "воскресенье", NORM: "воскресенье"},
-    {ORTH: "вскр", LEMMA: "воскресенье", NORM: "воскресенье"},
-    {ORTH: "воскр", LEMMA: "воскресенье", NORM: "воскресенье"},
+    {ORTH: "пн", NORM: "понедельник"},
+    {ORTH: "вт", NORM: "вторник"},
+    {ORTH: "ср", NORM: "среда"},
+    {ORTH: "чт", NORM: "четверг"},
+    {ORTH: "чтв", NORM: "четверг"},
+    {ORTH: "пт", NORM: "пятница"},
+    {ORTH: "сб", NORM: "суббота"},
+    {ORTH: "сбт", NORM: "суббота"},
+    {ORTH: "вс", NORM: "воскресенье"},
+    {ORTH: "вскр", NORM: "воскресенье"},
+    {ORTH: "воскр", NORM: "воскресенье"},
     # Months abbreviations
-    {ORTH: "янв", LEMMA: "январь", NORM: "январь"},
-    {ORTH: "фев", LEMMA: "февраль", NORM: "февраль"},
-    {ORTH: "февр", LEMMA: "февраль", NORM: "февраль"},
-    {ORTH: "мар", LEMMA: "март", NORM: "март"},
-    # {ORTH: "март", LEMMA: "март", NORM: "март"},
-    {ORTH: "мрт", LEMMA: "март", NORM: "март"},
-    {ORTH: "апр", LEMMA: "апрель", NORM: "апрель"},
-    # {ORTH: "май", LEMMA: "май", NORM: "май"},
-    {ORTH: "июн", LEMMA: "июнь", NORM: "июнь"},
-    # {ORTH: "июнь", LEMMA: "июнь", NORM: "июнь"},
-    {ORTH: "июл", LEMMA: "июль", NORM: "июль"},
-    # {ORTH: "июль", LEMMA: "июль", NORM: "июль"},
-    {ORTH: "авг", LEMMA: "август", NORM: "август"},
-    {ORTH: "сен", LEMMA: "сентябрь", NORM: "сентябрь"},
-    {ORTH: "сент", LEMMA: "сентябрь", NORM: "сентябрь"},
-    {ORTH: "окт", LEMMA: "октябрь", NORM: "октябрь"},
-    {ORTH: "октб", LEMMA: "октябрь", NORM: "октябрь"},
-    {ORTH: "ноя", LEMMA: "ноябрь", NORM: "ноябрь"},
-    {ORTH: "нояб", LEMMA: "ноябрь", NORM: "ноябрь"},
-    {ORTH: "нбр", LEMMA: "ноябрь", NORM: "ноябрь"},
-    {ORTH: "дек", LEMMA: "декабрь", NORM: "декабрь"},
+    {ORTH: "янв", NORM: "январь"},
+    {ORTH: "фев", NORM: "февраль"},
+    {ORTH: "февр", NORM: "февраль"},
+    {ORTH: "мар", NORM: "март"},
+    # {ORTH: "март", NORM: "март"},
+    {ORTH: "мрт", NORM: "март"},
+    {ORTH: "апр", NORM: "апрель"},
+    # {ORTH: "май", NORM: "май"},
+    {ORTH: "июн", NORM: "июнь"},
+    # {ORTH: "июнь", NORM: "июнь"},
+    {ORTH: "июл", NORM: "июль"},
+    # {ORTH: "июль", NORM: "июль"},
+    {ORTH: "авг", NORM: "август"},
+    {ORTH: "сен", NORM: "сентябрь"},
+    {ORTH: "сент", NORM: "сентябрь"},
+    {ORTH: "окт", NORM: "октябрь"},
+    {ORTH: "октб", NORM: "октябрь"},
+    {ORTH: "ноя", NORM: "ноябрь"},
+    {ORTH: "нояб", NORM: "ноябрь"},
+    {ORTH: "нбр", NORM: "ноябрь"},
+    {ORTH: "дек", NORM: "декабрь"},
 ]
 
 
 for abbrev_desc in _abbrev_exc:
     abbrev = abbrev_desc[ORTH]
     for orth in (abbrev, abbrev.capitalize(), abbrev.upper()):
-        _exc[orth] = [{ORTH: orth, LEMMA: abbrev_desc[LEMMA], NORM: abbrev_desc[NORM]}]
-        _exc[orth + "."] = [
-            {ORTH: orth + ".", LEMMA: abbrev_desc[LEMMA], NORM: abbrev_desc[NORM]}
-        ]
+        _exc[orth] = [{ORTH: orth, NORM: abbrev_desc[NORM]}]
+        _exc[orth + "."] = [{ORTH: orth + ".", NORM: abbrev_desc[NORM]}]
 
 
 _slang_exc = [
-    {ORTH: "2к15", LEMMA: "2015", NORM: "2015"},
-    {ORTH: "2к16", LEMMA: "2016", NORM: "2016"},
-    {ORTH: "2к17", LEMMA: "2017", NORM: "2017"},
-    {ORTH: "2к18", LEMMA: "2018", NORM: "2018"},
-    {ORTH: "2к19", LEMMA: "2019", NORM: "2019"},
-    {ORTH: "2к20", LEMMA: "2020", NORM: "2020"},
+    {ORTH: "2к15", NORM: "2015"},
+    {ORTH: "2к16", NORM: "2016"},
+    {ORTH: "2к17", NORM: "2017"},
+    {ORTH: "2к18", NORM: "2018"},
+    {ORTH: "2к19", NORM: "2019"},
+    {ORTH: "2к20", NORM: "2020"},
 ]
 
 for slang_desc in _slang_exc:
diff --git a/spacy/lang/sr/tokenizer_exceptions.py b/spacy/lang/sr/tokenizer_exceptions.py
index a41fe7e4e..dcaa3e239 100755
--- a/spacy/lang/sr/tokenizer_exceptions.py
+++ b/spacy/lang/sr/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -7,85 +7,83 @@ _exc = {}
 
 _abbrev_exc = [
     # Weekdays abbreviations
-    {ORTH: "пoн", LEMMA: "понедељак", NORM: "понедељак"},
-    {ORTH: "уто", LEMMA: "уторак", NORM: "уторак"},
-    {ORTH: "сре", LEMMA: "среда", NORM: "среда"},
-    {ORTH: "чет", LEMMA: "четвртак", NORM: "четвртак"},
-    {ORTH: "пет", LEMMA: "петак", NORM: "петак"},
-    {ORTH: "суб", LEMMA: "субота", NORM: "субота"},
-    {ORTH: "нед", LEMMA: "недеља", NORM: "недеља"},
+    {ORTH: "пoн", NORM: "понедељак"},
+    {ORTH: "уто", NORM: "уторак"},
+    {ORTH: "сре", NORM: "среда"},
+    {ORTH: "чет", NORM: "четвртак"},
+    {ORTH: "пет", NORM: "петак"},
+    {ORTH: "суб", NORM: "субота"},
+    {ORTH: "нед", NORM: "недеља"},
     # Months abbreviations
-    {ORTH: "јан", LEMMA: "јануар", NORM: "јануар"},
-    {ORTH: "феб", LEMMA: "фебруар", NORM: "фебруар"},
-    {ORTH: "мар", LEMMA: "март", NORM: "март"},
-    {ORTH: "апр", LEMMA: "април", NORM: "април"},
-    {ORTH: "јуни", LEMMA: "јун", NORM: "јун"},
-    {ORTH: "јули", LEMMA: "јул", NORM: "јул"},
-    {ORTH: "авг", LEMMA: "август", NORM: "август"},
-    {ORTH: "сеп", LEMMA: "септембар", NORM: "септембар"},
-    {ORTH: "септ", LEMMA: "септембар", NORM: "септембар"},
-    {ORTH: "окт", LEMMA: "октобар", NORM: "октобар"},
-    {ORTH: "нов", LEMMA: "новембар", NORM: "новембар"},
-    {ORTH: "дец", LEMMA: "децембар", NORM: "децембар"},
+    {ORTH: "јан", NORM: "јануар"},
+    {ORTH: "феб", NORM: "фебруар"},
+    {ORTH: "мар", NORM: "март"},
+    {ORTH: "апр", NORM: "април"},
+    {ORTH: "јуни", NORM: "јун"},
+    {ORTH: "јули", NORM: "јул"},
+    {ORTH: "авг", NORM: "август"},
+    {ORTH: "сеп", NORM: "септембар"},
+    {ORTH: "септ", NORM: "септембар"},
+    {ORTH: "окт", NORM: "октобар"},
+    {ORTH: "нов", NORM: "новембар"},
+    {ORTH: "дец", NORM: "децембар"},
 ]
 
 
 for abbrev_desc in _abbrev_exc:
     abbrev = abbrev_desc[ORTH]
     for orth in (abbrev, abbrev.capitalize(), abbrev.upper()):
-        _exc[orth] = [{ORTH: orth, LEMMA: abbrev_desc[LEMMA], NORM: abbrev_desc[NORM]}]
-        _exc[orth + "."] = [
-            {ORTH: orth + ".", LEMMA: abbrev_desc[LEMMA], NORM: abbrev_desc[NORM]}
-        ]
+        _exc[orth] = [{ORTH: orth, NORM: abbrev_desc[NORM]}]
+        _exc[orth + "."] = [{ORTH: orth + ".", NORM: abbrev_desc[NORM]}]
 
 
 # common abbreviations
 _slang_exc = [
     # without dot
-    {ORTH: "др", LEMMA: "доктор", NORM: "доктор"},
-    {ORTH: "гдин", LEMMA: "господин", NORM: "господин"},
-    {ORTH: "гђа", LEMMA: "госпођа", NORM: "госпођа"},
-    {ORTH: "гђица", LEMMA: "госпођица", NORM: "госпођица"},
-    {ORTH: "мр", LEMMA: "магистар", NORM: "магистар"},
-    {ORTH: "Бгд", LEMMA: "Београд", NORM: "београд"},
-    {ORTH: "цм", LEMMA: "центиметар", NORM: "центиметар"},
-    {ORTH: "м", LEMMA: "метар", NORM: "метар"},
-    {ORTH: "км", LEMMA: "километар", NORM: "километар"},
-    {ORTH: "мг", LEMMA: "милиграм", NORM: "милиграм"},
-    {ORTH: "кг", LEMMA: "килограм", NORM: "килограм"},
-    {ORTH: "дл", LEMMA: "децилитар", NORM: "децилитар"},
-    {ORTH: "хл", LEMMA: "хектолитар", NORM: "хектолитар"},
+    {ORTH: "др", NORM: "доктор"},
+    {ORTH: "гдин", NORM: "господин"},
+    {ORTH: "гђа", NORM: "госпођа"},
+    {ORTH: "гђица", NORM: "госпођица"},
+    {ORTH: "мр", NORM: "магистар"},
+    {ORTH: "Бгд", NORM: "београд"},
+    {ORTH: "цм", NORM: "центиметар"},
+    {ORTH: "м", NORM: "метар"},
+    {ORTH: "км", NORM: "километар"},
+    {ORTH: "мг", NORM: "милиграм"},
+    {ORTH: "кг", NORM: "килограм"},
+    {ORTH: "дл", NORM: "децилитар"},
+    {ORTH: "хл", NORM: "хектолитар"},
     # with dot
-    {ORTH: "ул.", LEMMA: "улица", NORM: "улица"},
-    {ORTH: "бр.", LEMMA: "број", NORM: "број"},
-    {ORTH: "нпр.", LEMMA: "на пример", NORM: "на пример"},
-    {ORTH: "тзв.", LEMMA: "такозван", NORM: "такозван"},
-    {ORTH: "проф.", LEMMA: "професор", NORM: "професор"},
-    {ORTH: "стр.", LEMMA: "страна", NORM: "страна"},
-    {ORTH: "једн.", LEMMA: "једнина", NORM: "једнина"},
-    {ORTH: "мн.", LEMMA: "множина", NORM: "множина"},
-    {ORTH: "уч.", LEMMA: "ученик", NORM: "ученик"},
-    {ORTH: "разр.", LEMMA: "разред", NORM: "разред"},
-    {ORTH: "инж.", LEMMA: "инжењер", NORM: "инжењер"},
-    {ORTH: "гимн.", LEMMA: "гимназија", NORM: "гимназија"},
-    {ORTH: "год.", LEMMA: "година", NORM: "година"},
-    {ORTH: "мед.", LEMMA: "медицина", NORM: "медицина"},
-    {ORTH: "гимн.", LEMMA: "гимназија", NORM: "гимназија"},
-    {ORTH: "акад.", LEMMA: "академик", NORM: "академик"},
-    {ORTH: "доц.", LEMMA: "доцент", NORM: "доцент"},
-    {ORTH: "итд.", LEMMA: "и тако даље", NORM: "и тако даље"},
-    {ORTH: "и сл.", LEMMA: "и слично", NORM: "и слично"},
-    {ORTH: "н.е.", LEMMA: "нова ера", NORM: "нове ере"},
-    {ORTH: "о.г.", LEMMA: "ова година", NORM: "ове године"},
-    {ORTH: "л.к.", LEMMA: "лична карта", NORM: "лична карта"},
-    {ORTH: "в.д.", LEMMA: "вршилац дужности", NORM: "вршилац дужности"},
-    {ORTH: "стр.", LEMMA: "страна", NORM: "страна"},
+    {ORTH: "ул.", NORM: "улица"},
+    {ORTH: "бр.", NORM: "број"},
+    {ORTH: "нпр.", NORM: "на пример"},
+    {ORTH: "тзв.", NORM: "такозван"},
+    {ORTH: "проф.", NORM: "професор"},
+    {ORTH: "стр.", NORM: "страна"},
+    {ORTH: "једн.", NORM: "једнина"},
+    {ORTH: "мн.", NORM: "множина"},
+    {ORTH: "уч.", NORM: "ученик"},
+    {ORTH: "разр.", NORM: "разред"},
+    {ORTH: "инж.", NORM: "инжењер"},
+    {ORTH: "гимн.", NORM: "гимназија"},
+    {ORTH: "год.", NORM: "година"},
+    {ORTH: "мед.", NORM: "медицина"},
+    {ORTH: "гимн.", NORM: "гимназија"},
+    {ORTH: "акад.", NORM: "академик"},
+    {ORTH: "доц.", NORM: "доцент"},
+    {ORTH: "итд.", NORM: "и тако даље"},
+    {ORTH: "и сл.", NORM: "и слично"},
+    {ORTH: "н.е.", NORM: "нове ере"},
+    {ORTH: "о.г.", NORM: "ове године"},
+    {ORTH: "л.к.", NORM: "лична карта"},
+    {ORTH: "в.д.", NORM: "вршилац дужности"},
+    {ORTH: "стр.", NORM: "страна"},
     # with qoute
-    {ORTH: "ал'", LEMMA: "али", NORM: "али"},
-    {ORTH: "ил'", LEMMA: "или", NORM: "или"},
-    {ORTH: "је л'", LEMMA: "је ли", NORM: "је ли"},
-    {ORTH: "да л'", LEMMA: "да ли", NORM: "да ли"},
-    {ORTH: "држ'те", LEMMA: "држати", NORM: "држите"},
+    {ORTH: "ал'", NORM: "али"},
+    {ORTH: "ил'", NORM: "или"},
+    {ORTH: "је л'", NORM: "је ли"},
+    {ORTH: "да л'", NORM: "да ли"},
+    {ORTH: "држ'те", NORM: "држите"},
 ]
 
 for slang_desc in _slang_exc:
diff --git a/spacy/lang/sv/tokenizer_exceptions.py b/spacy/lang/sv/tokenizer_exceptions.py
index f1b914bff..64206f2f2 100644
--- a/spacy/lang/sv/tokenizer_exceptions.py
+++ b/spacy/lang/sv/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import LEMMA, NORM, ORTH, PRON_LEMMA
+from ...symbols import NORM, ORTH
 from ...util import update_exc
 
 _exc = {}
@@ -10,61 +10,58 @@ _exc = {}
 for verb_data in [
     {ORTH: "driver"},
     {ORTH: "kör"},
-    {ORTH: "hörr", LEMMA: "hör"},
+    {ORTH: "hörr"},
     {ORTH: "fattar"},
-    {ORTH: "hajar", LEMMA: "förstår"},
+    {ORTH: "hajar"},
     {ORTH: "lever"},
-    {ORTH: "serr", LEMMA: "ser"},
+    {ORTH: "serr"},
     {ORTH: "fixar"},
 ]:
     verb_data_tc = dict(verb_data)
     verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
     for data in [verb_data, verb_data_tc]:
-        _exc[data[ORTH] + "u"] = [
-            dict(data),
-            {ORTH: "u", LEMMA: PRON_LEMMA, NORM: "du"},
-        ]
+        _exc[data[ORTH] + "u"] = [data, {ORTH: "u", NORM: "du"}]
 
 # Abbreviations for weekdays "sön." (for "söndag" / "söner")
 # are left out because they are ambiguous. The same is the case
 # for abbreviations "jul." and "Jul." ("juli" / "jul").
 for exc_data in [
-    {ORTH: "jan.", LEMMA: "januari"},
-    {ORTH: "febr.", LEMMA: "februari"},
-    {ORTH: "feb.", LEMMA: "februari"},
-    {ORTH: "apr.", LEMMA: "april"},
-    {ORTH: "jun.", LEMMA: "juni"},
-    {ORTH: "aug.", LEMMA: "augusti"},
-    {ORTH: "sept.", LEMMA: "september"},
-    {ORTH: "sep.", LEMMA: "september"},
-    {ORTH: "okt.", LEMMA: "oktober"},
-    {ORTH: "nov.", LEMMA: "november"},
-    {ORTH: "dec.", LEMMA: "december"},
-    {ORTH: "mån.", LEMMA: "måndag"},
-    {ORTH: "tis.", LEMMA: "tisdag"},
-    {ORTH: "ons.", LEMMA: "onsdag"},
-    {ORTH: "tors.", LEMMA: "torsdag"},
-    {ORTH: "fre.", LEMMA: "fredag"},
-    {ORTH: "lör.", LEMMA: "lördag"},
-    {ORTH: "Jan.", LEMMA: "Januari"},
-    {ORTH: "Febr.", LEMMA: "Februari"},
-    {ORTH: "Feb.", LEMMA: "Februari"},
-    {ORTH: "Apr.", LEMMA: "April"},
-    {ORTH: "Jun.", LEMMA: "Juni"},
-    {ORTH: "Aug.", LEMMA: "Augusti"},
-    {ORTH: "Sept.", LEMMA: "September"},
-    {ORTH: "Sep.", LEMMA: "September"},
-    {ORTH: "Okt.", LEMMA: "Oktober"},
-    {ORTH: "Nov.", LEMMA: "November"},
-    {ORTH: "Dec.", LEMMA: "December"},
-    {ORTH: "Mån.", LEMMA: "Måndag"},
-    {ORTH: "Tis.", LEMMA: "Tisdag"},
-    {ORTH: "Ons.", LEMMA: "Onsdag"},
-    {ORTH: "Tors.", LEMMA: "Torsdag"},
-    {ORTH: "Fre.", LEMMA: "Fredag"},
-    {ORTH: "Lör.", LEMMA: "Lördag"},
-    {ORTH: "sthlm", LEMMA: "Stockholm"},
-    {ORTH: "gbg", LEMMA: "Göteborg"},
+    {ORTH: "jan.", NORM: "januari"},
+    {ORTH: "febr.", NORM: "februari"},
+    {ORTH: "feb.", NORM: "februari"},
+    {ORTH: "apr.", NORM: "april"},
+    {ORTH: "jun.", NORM: "juni"},
+    {ORTH: "aug.", NORM: "augusti"},
+    {ORTH: "sept.", NORM: "september"},
+    {ORTH: "sep.", NORM: "september"},
+    {ORTH: "okt.", NORM: "oktober"},
+    {ORTH: "nov.", NORM: "november"},
+    {ORTH: "dec.", NORM: "december"},
+    {ORTH: "mån.", NORM: "måndag"},
+    {ORTH: "tis.", NORM: "tisdag"},
+    {ORTH: "ons.", NORM: "onsdag"},
+    {ORTH: "tors.", NORM: "torsdag"},
+    {ORTH: "fre.", NORM: "fredag"},
+    {ORTH: "lör.", NORM: "lördag"},
+    {ORTH: "Jan.", NORM: "Januari"},
+    {ORTH: "Febr.", NORM: "Februari"},
+    {ORTH: "Feb.", NORM: "Februari"},
+    {ORTH: "Apr.", NORM: "April"},
+    {ORTH: "Jun.", NORM: "Juni"},
+    {ORTH: "Aug.", NORM: "Augusti"},
+    {ORTH: "Sept.", NORM: "September"},
+    {ORTH: "Sep.", NORM: "September"},
+    {ORTH: "Okt.", NORM: "Oktober"},
+    {ORTH: "Nov.", NORM: "November"},
+    {ORTH: "Dec.", NORM: "December"},
+    {ORTH: "Mån.", NORM: "Måndag"},
+    {ORTH: "Tis.", NORM: "Tisdag"},
+    {ORTH: "Ons.", NORM: "Onsdag"},
+    {ORTH: "Tors.", NORM: "Torsdag"},
+    {ORTH: "Fre.", NORM: "Fredag"},
+    {ORTH: "Lör.", NORM: "Lördag"},
+    {ORTH: "sthlm", NORM: "Stockholm"},
+    {ORTH: "gbg", NORM: "Göteborg"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
@@ -154,6 +151,6 @@ for orth in ABBREVIATIONS:
 # Sentences ending in "i." (as in "... peka i."), "m." (as in "...än 2000 m."),
 # should be tokenized as two separate tokens.
 for orth in ["i", "m"]:
-    _exc[orth + "."] = [{ORTH: orth, LEMMA: orth, NORM: orth}, {ORTH: "."}]
+    _exc[orth + "."] = [{ORTH: orth, NORM: orth, NORM: orth}, {ORTH: "."}]
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
diff --git a/spacy/lang/th/tokenizer_exceptions.py b/spacy/lang/th/tokenizer_exceptions.py
index 0529b3a99..92116d474 100644
--- a/spacy/lang/th/tokenizer_exceptions.py
+++ b/spacy/lang/th/tokenizer_exceptions.py
@@ -1,469 +1,438 @@
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH
 
 
 _exc = {
     # หน่วยงานรัฐ / government agency
-    "กกต.": [{ORTH: "กกต.", LEMMA: "คณะกรรมการการเลือกตั้ง"}],
-    "กทท.": [{ORTH: "กทท.", LEMMA: "การท่าเรือแห่งประเทศไทย"}],
-    "กทพ.": [{ORTH: "กทพ.", LEMMA: "การทางพิเศษแห่งประเทศไทย"}],
-    "กบข.": [{ORTH: "กบข.", LEMMA: "กองทุนบำเหน็จบำนาญข้าราชการพลเรือน"}],
-    "กบว.": [{ORTH: "กบว.", LEMMA: "คณะกรรมการบริหารวิทยุกระจายเสียงและวิทยุโทรทัศน์"}],
-    "กปน.": [{ORTH: "กปน.", LEMMA: "การประปานครหลวง"}],
-    "กปภ.": [{ORTH: "กปภ.", LEMMA: "การประปาส่วนภูมิภาค"}],
-    "กปส.": [{ORTH: "กปส.", LEMMA: "กรมประชาสัมพันธ์"}],
-    "กผม.": [{ORTH: "กผม.", LEMMA: "กองผังเมือง"}],
-    "กฟน.": [{ORTH: "กฟน.", LEMMA: "การไฟฟ้านครหลวง"}],
-    "กฟผ.": [{ORTH: "กฟผ.", LEMMA: "การไฟฟ้าฝ่ายผลิตแห่งประเทศไทย"}],
-    "กฟภ.": [{ORTH: "กฟภ.", LEMMA: "การไฟฟ้าส่วนภูมิภาค"}],
-    "ก.ช.น.": [{ORTH: "ก.ช.น.", LEMMA: "คณะกรรมการช่วยเหลือชาวนาชาวไร่"}],
-    "กยศ.": [{ORTH: "กยศ.", LEMMA: "กองทุนเงินให้กู้ยืมเพื่อการศึกษา"}],
-    "ก.ล.ต.": [{ORTH: "ก.ล.ต.", LEMMA: "คณะกรรมการกำกับหลักทรัพย์และตลาดหลักทรัพย์"}],
-    "กศ.บ.": [{ORTH: "กศ.บ.", LEMMA: "การศึกษาบัณฑิต"}],
-    "กศน.": [{ORTH: "กศน.", LEMMA: "กรมการศึกษานอกโรงเรียน"}],
-    "กสท.": [{ORTH: "กสท.", LEMMA: "การสื่อสารแห่งประเทศไทย"}],
-    "กอ.รมน.": [{ORTH: "กอ.รมน.", LEMMA: "กองอำนวยการรักษาความมั่นคงภายใน"}],
-    "กร.": [{ORTH: "กร.", LEMMA: "กองเรือยุทธการ"}],
-    "ขสมก.": [{ORTH: "ขสมก.", LEMMA: "องค์การขนส่งมวลชนกรุงเทพ"}],
-    "คตง.": [{ORTH: "คตง.", LEMMA: "คณะกรรมการตรวจเงินแผ่นดิน"}],
-    "ครม.": [{ORTH: "ครม.", LEMMA: "คณะรัฐมนตรี"}],
-    "คมช.": [{ORTH: "คมช.", LEMMA: "คณะมนตรีความมั่นคงแห่งชาติ"}],
-    "ตชด.": [{ORTH: "ตชด.", LEMMA: "ตำรวจตะเวนชายเดน"}],
-    "ตม.": [{ORTH: "ตม.", LEMMA: "กองตรวจคนเข้าเมือง"}],
-    "ตร.": [{ORTH: "ตร.", LEMMA: "ตำรวจ"}],
-    "ททท.": [{ORTH: "ททท.", LEMMA: "การท่องเที่ยวแห่งประเทศไทย"}],
-    "ททบ.": [{ORTH: "ททบ.", LEMMA: "สถานีวิทยุโทรทัศน์กองทัพบก"}],
-    "ทบ.": [{ORTH: "ทบ.", LEMMA: "กองทัพบก"}],
-    "ทร.": [{ORTH: "ทร.", LEMMA: "กองทัพเรือ"}],
-    "ทอ.": [{ORTH: "ทอ.", LEMMA: "กองทัพอากาศ"}],
-    "ทอท.": [{ORTH: "ทอท.", LEMMA: "การท่าอากาศยานแห่งประเทศไทย"}],
-    "ธ.ก.ส.": [{ORTH: "ธ.ก.ส.", LEMMA: "ธนาคารเพื่อการเกษตรและสหกรณ์การเกษตร"}],
-    "ธปท.": [{ORTH: "ธปท.", LEMMA: "ธนาคารแห่งประเทศไทย"}],
-    "ธอส.": [{ORTH: "ธอส.", LEMMA: "ธนาคารอาคารสงเคราะห์"}],
-    "นย.": [{ORTH: "นย.", LEMMA: "นาวิกโยธิน"}],
-    "ปตท.": [{ORTH: "ปตท.", LEMMA: "การปิโตรเลียมแห่งประเทศไทย"}],
-    "ป.ป.ช.": [
-        {
-            ORTH: "ป.ป.ช.",
-            LEMMA: "คณะกรรมการป้องกันและปราบปรามการทุจริตและประพฤติมิชอบในวงราชการ",
-        }
-    ],
-    "ป.ป.ส.": [{ORTH: "ป.ป.ส.", LEMMA: "คณะกรรมการป้องกันและปราบปรามยาเสพติด"}],
-    "บพร.": [{ORTH: "บพร.", LEMMA: "กรมการบินพลเรือน"}],
-    "บย.": [{ORTH: "บย.", LEMMA: "กองบินยุทธการ"}],
-    "พสวท.": [
-        {
-            ORTH: "พสวท.",
-            LEMMA: "โครงการพัฒนาและส่งเสริมผู้มีความรู้ความสามารถพิเศษทางวิทยาศาสตร์และเทคโนโลยี",
-        }
-    ],
-    "มอก.": [{ORTH: "มอก.", LEMMA: "สำนักงานมาตรฐานผลิตภัณฑ์อุตสาหกรรม"}],
-    "ยธ.": [{ORTH: "ยธ.", LEMMA: "กรมโยธาธิการ"}],
-    "รพช.": [{ORTH: "รพช.", LEMMA: "สำนักงานเร่งรัดพัฒนาชนบท"}],
-    "รฟท.": [{ORTH: "รฟท.", LEMMA: "การรถไฟแห่งประเทศไทย"}],
-    "รฟม.": [{ORTH: "รฟม.", LEMMA: "การรถไฟฟ้าขนส่งมวลชนแห่งประเทศไทย"}],
-    "ศธ.": [{ORTH: "ศธ.", LEMMA: "กระทรวงศึกษาธิการ"}],
-    "ศนธ.": [{ORTH: "ศนธ.", LEMMA: "ศูนย์กลางนิสิตนักศึกษาแห่งประเทศไทย"}],
-    "สกจ.": [{ORTH: "สกจ.", LEMMA: "สหกรณ์จังหวัด"}],
-    "สกท.": [{ORTH: "สกท.", LEMMA: "สำนักงานคณะกรรมการส่งเสริมการลงทุน"}],
-    "สกว.": [{ORTH: "สกว.", LEMMA: "สำนักงานกองทุนสนับสนุนการวิจัย"}],
-    "สคบ.": [{ORTH: "สคบ.", LEMMA: "สำนักงานคณะกรรมการคุ้มครองผู้บริโภค"}],
-    "สจร.": [{ORTH: "สจร.", LEMMA: "สำนักงานคณะกรรมการจัดระบบการจราจรทางบก"}],
-    "สตง.": [{ORTH: "สตง.", LEMMA: "สำนักงานตรวจเงินแผ่นดิน"}],
-    "สทท.": [{ORTH: "สทท.", LEMMA: "สถานีวิทยุโทรทัศน์แห่งประเทศไทย"}],
-    "สทร.": [{ORTH: "สทร.", LEMMA: "สำนักงานกลางทะเบียนราษฎร์"}],
-    "สธ": [{ORTH: "สธ", LEMMA: "กระทรวงสาธารณสุข"}],
-    "สนช.": [{ORTH: "สนช.", LEMMA: "สภานิติบัญญัติแห่งชาติ,สำนักงานนวัตกรรมแห่งชาติ"}],
-    "สนนท.": [{ORTH: "สนนท.", LEMMA: "สหพันธ์นิสิตนักศึกษาแห่งประเทศไทย"}],
-    "สปก.": [{ORTH: "สปก.", LEMMA: "สำนักงานการปฏิรูปที่ดินเพื่อเกษตรกรรม"}],
-    "สปช.": [{ORTH: "สปช.", LEMMA: "สำนักงานคณะกรรมการการประถมศึกษาแห่งชาติ"}],
-    "สปอ.": [{ORTH: "สปอ.", LEMMA: "สำนักงานการประถมศึกษาอำเภอ"}],
-    "สพช.": [{ORTH: "สพช.", LEMMA: "สำนักงานคณะกรรมการนโยบายพลังงานแห่งชาติ"}],
-    "สยช.": [
-        {ORTH: "สยช.", LEMMA: "สำนักงานคณะกรรมการส่งเสริมและประสานงานเยาวชนแห่งชาติ"}
-    ],
-    "สวช.": [{ORTH: "สวช.", LEMMA: "สำนักงานคณะกรรมการวัฒนธรรมแห่งชาติ"}],
-    "สวท.": [{ORTH: "สวท.", LEMMA: "สถานีวิทยุกระจายเสียงแห่งประเทศไทย"}],
-    "สวทช.": [{ORTH: "สวทช.", LEMMA: "สำนักงานพัฒนาวิทยาศาสตร์และเทคโนโลยีแห่งชาติ"}],
-    "สคช.": [
-        {ORTH: "สคช.", LEMMA: "สำนักงานคณะกรรมการพัฒนาการเศรษฐกิจและสังคมแห่งชาติ"}
-    ],
-    "สสว.": [{ORTH: "สสว.", LEMMA: "สำนักงานส่งเสริมวิสาหกิจขนาดกลางและขนาดย่อม"}],
-    "สสส.": [{ORTH: "สสส.", LEMMA: "สำนักงานกองทุนสนับสนุนการสร้างเสริมสุขภาพ"}],
-    "สสวท.": [{ORTH: "สสวท.", LEMMA: "สถาบันส่งเสริมการสอนวิทยาศาสตร์และเทคโนโลยี"}],
-    "อตก.": [{ORTH: "อตก.", LEMMA: "องค์การตลาดเพื่อเกษตรกร"}],
-    "อบจ.": [{ORTH: "อบจ.", LEMMA: "องค์การบริหารส่วนจังหวัด"}],
-    "อบต.": [{ORTH: "อบต.", LEMMA: "องค์การบริหารส่วนตำบล"}],
-    "อปพร.": [{ORTH: "อปพร.", LEMMA: "อาสาสมัครป้องกันภัยฝ่ายพลเรือน"}],
-    "อย.": [{ORTH: "อย.", LEMMA: "สำนักงานคณะกรรมการอาหารและยา"}],
-    "อ.ส.ม.ท.": [{ORTH: "อ.ส.ม.ท.", LEMMA: "องค์การสื่อสารมวลชนแห่งประเทศไทย"}],
+    "กกต.": [{ORTH: "กกต."}],
+    "กทท.": [{ORTH: "กทท."}],
+    "กทพ.": [{ORTH: "กทพ."}],
+    "กบข.": [{ORTH: "กบข."}],
+    "กบว.": [{ORTH: "กบว."}],
+    "กปน.": [{ORTH: "กปน."}],
+    "กปภ.": [{ORTH: "กปภ."}],
+    "กปส.": [{ORTH: "กปส."}],
+    "กผม.": [{ORTH: "กผม."}],
+    "กฟน.": [{ORTH: "กฟน."}],
+    "กฟผ.": [{ORTH: "กฟผ."}],
+    "กฟภ.": [{ORTH: "กฟภ."}],
+    "ก.ช.น.": [{ORTH: "ก.ช.น."}],
+    "กยศ.": [{ORTH: "กยศ."}],
+    "ก.ล.ต.": [{ORTH: "ก.ล.ต."}],
+    "กศ.บ.": [{ORTH: "กศ.บ."}],
+    "กศน.": [{ORTH: "กศน."}],
+    "กสท.": [{ORTH: "กสท."}],
+    "กอ.รมน.": [{ORTH: "กอ.รมน."}],
+    "กร.": [{ORTH: "กร."}],
+    "ขสมก.": [{ORTH: "ขสมก."}],
+    "คตง.": [{ORTH: "คตง."}],
+    "ครม.": [{ORTH: "ครม."}],
+    "คมช.": [{ORTH: "คมช."}],
+    "ตชด.": [{ORTH: "ตชด."}],
+    "ตม.": [{ORTH: "ตม."}],
+    "ตร.": [{ORTH: "ตร."}],
+    "ททท.": [{ORTH: "ททท."}],
+    "ททบ.": [{ORTH: "ททบ."}],
+    "ทบ.": [{ORTH: "ทบ."}],
+    "ทร.": [{ORTH: "ทร."}],
+    "ทอ.": [{ORTH: "ทอ."}],
+    "ทอท.": [{ORTH: "ทอท."}],
+    "ธ.ก.ส.": [{ORTH: "ธ.ก.ส."}],
+    "ธปท.": [{ORTH: "ธปท."}],
+    "ธอส.": [{ORTH: "ธอส."}],
+    "นย.": [{ORTH: "นย."}],
+    "ปตท.": [{ORTH: "ปตท."}],
+    "ป.ป.ช.": [{ORTH: "ป.ป.ช."}],
+    "ป.ป.ส.": [{ORTH: "ป.ป.ส."}],
+    "บพร.": [{ORTH: "บพร."}],
+    "บย.": [{ORTH: "บย."}],
+    "พสวท.": [{ORTH: "พสวท."}],
+    "มอก.": [{ORTH: "มอก."}],
+    "ยธ.": [{ORTH: "ยธ."}],
+    "รพช.": [{ORTH: "รพช."}],
+    "รฟท.": [{ORTH: "รฟท."}],
+    "รฟม.": [{ORTH: "รฟม."}],
+    "ศธ.": [{ORTH: "ศธ."}],
+    "ศนธ.": [{ORTH: "ศนธ."}],
+    "สกจ.": [{ORTH: "สกจ."}],
+    "สกท.": [{ORTH: "สกท."}],
+    "สกว.": [{ORTH: "สกว."}],
+    "สคบ.": [{ORTH: "สคบ."}],
+    "สจร.": [{ORTH: "สจร."}],
+    "สตง.": [{ORTH: "สตง."}],
+    "สทท.": [{ORTH: "สทท."}],
+    "สทร.": [{ORTH: "สทร."}],
+    "สธ": [{ORTH: "สธ"}],
+    "สนช.": [{ORTH: "สนช."}],
+    "สนนท.": [{ORTH: "สนนท."}],
+    "สปก.": [{ORTH: "สปก."}],
+    "สปช.": [{ORTH: "สปช."}],
+    "สปอ.": [{ORTH: "สปอ."}],
+    "สพช.": [{ORTH: "สพช."}],
+    "สยช.": [{ORTH: "สยช."}],
+    "สวช.": [{ORTH: "สวช."}],
+    "สวท.": [{ORTH: "สวท."}],
+    "สวทช.": [{ORTH: "สวทช."}],
+    "สคช.": [{ORTH: "สคช."}],
+    "สสว.": [{ORTH: "สสว."}],
+    "สสส.": [{ORTH: "สสส."}],
+    "สสวท.": [{ORTH: "สสวท."}],
+    "อตก.": [{ORTH: "อตก."}],
+    "อบจ.": [{ORTH: "อบจ."}],
+    "อบต.": [{ORTH: "อบต."}],
+    "อปพร.": [{ORTH: "อปพร."}],
+    "อย.": [{ORTH: "อย."}],
+    "อ.ส.ม.ท.": [{ORTH: "อ.ส.ม.ท."}],
     # มหาวิทยาลัย / สถานศึกษา / university / college
-    "มทส.": [{ORTH: "มทส.", LEMMA: "มหาวิทยาลัยเทคโนโลยีสุรนารี"}],
-    "มธ.": [{ORTH: "มธ.", LEMMA: "มหาวิทยาลัยธรรมศาสตร์"}],
-    "ม.อ.": [{ORTH: "ม.อ.", LEMMA: "มหาวิทยาลัยสงขลานครินทร์"}],
-    "มทร.": [{ORTH: "มทร.", LEMMA: "มหาวิทยาลัยเทคโนโลยีราชมงคล"}],
-    "มมส.": [{ORTH: "มมส.", LEMMA: "มหาวิทยาลัยมหาสารคาม"}],
-    "วท.": [{ORTH: "วท.", LEMMA: "วิทยาลัยเทคนิค"}],
-    "สตม.": [{ORTH: "สตม.", LEMMA: "สำนักงานตรวจคนเข้าเมือง (ตำรวจ)"}],
+    "มทส.": [{ORTH: "มทส."}],
+    "มธ.": [{ORTH: "มธ."}],
+    "ม.อ.": [{ORTH: "ม.อ."}],
+    "มทร.": [{ORTH: "มทร."}],
+    "มมส.": [{ORTH: "มมส."}],
+    "วท.": [{ORTH: "วท."}],
+    "สตม.": [{ORTH: "สตม."}],
     # ยศ / rank
-    "ดร.": [{ORTH: "ดร.", LEMMA: "ดอกเตอร์"}],
-    "ด.ต.": [{ORTH: "ด.ต.", LEMMA: "ดาบตำรวจ"}],
-    "จ.ต.": [{ORTH: "จ.ต.", LEMMA: "จ่าตรี"}],
-    "จ.ท.": [{ORTH: "จ.ท.", LEMMA: "จ่าโท"}],
-    "จ.ส.ต.": [{ORTH: "จ.ส.ต.", LEMMA: "จ่าสิบตรี (ทหารบก)"}],
-    "จสต.": [{ORTH: "จสต.", LEMMA: "จ่าสิบตำรวจ"}],
-    "จ.ส.ท.": [{ORTH: "จ.ส.ท.", LEMMA: "จ่าสิบโท"}],
-    "จ.ส.อ.": [{ORTH: "จ.ส.อ.", LEMMA: "จ่าสิบเอก"}],
-    "จ.อ.": [{ORTH: "จ.อ.", LEMMA: "จ่าเอก"}],
-    "ทพญ.": [{ORTH: "ทพญ.", LEMMA: "ทันตแพทย์หญิง"}],
-    "ทนพ.": [{ORTH: "ทนพ.", LEMMA: "เทคนิคการแพทย์"}],
-    "นจอ.": [{ORTH: "นจอ.", LEMMA: "นักเรียนจ่าอากาศ"}],
-    "น.ช.": [{ORTH: "น.ช.", LEMMA: "นักโทษชาย"}],
-    "น.ญ.": [{ORTH: "น.ญ.", LEMMA: "นักโทษหญิง"}],
-    "น.ต.": [{ORTH: "น.ต.", LEMMA: "นาวาตรี"}],
-    "น.ท.": [{ORTH: "น.ท.", LEMMA: "นาวาโท"}],
-    "นตท.": [{ORTH: "นตท.", LEMMA: "นักเรียนเตรียมทหาร"}],
-    "นนส.": [{ORTH: "นนส.", LEMMA: "นักเรียนนายสิบทหารบก"}],
-    "นนร.": [{ORTH: "นนร.", LEMMA: "นักเรียนนายร้อย"}],
-    "นนอ.": [{ORTH: "นนอ.", LEMMA: "นักเรียนนายเรืออากาศ"}],
-    "นพ.": [{ORTH: "นพ.", LEMMA: "นายแพทย์"}],
-    "นพท.": [{ORTH: "นพท.", LEMMA: "นายแพทย์ทหาร"}],
-    "นรจ.": [{ORTH: "นรจ.", LEMMA: "นักเรียนจ่าทหารเรือ"}],
-    "นรต.": [{ORTH: "นรต.", LEMMA: "นักเรียนนายร้อยตำรวจ"}],
-    "นศพ.": [{ORTH: "นศพ.", LEMMA: "นักศึกษาแพทย์"}],
-    "นศท.": [{ORTH: "นศท.", LEMMA: "นักศึกษาวิชาทหาร"}],
-    "น.สพ.": [{ORTH: "น.สพ.", LEMMA: "นายสัตวแพทย์ (พ.ร.บ.วิชาชีพการสัตวแพทย์)"}],
-    "น.อ.": [{ORTH: "น.อ.", LEMMA: "นาวาเอก"}],
-    "บช.ก.": [{ORTH: "บช.ก.", LEMMA: "กองบัญชาการตำรวจสอบสวนกลาง"}],
-    "บช.น.": [{ORTH: "บช.น.", LEMMA: "กองบัญชาการตำรวจนครบาล"}],
-    "ผกก.": [{ORTH: "ผกก.", LEMMA: "ผู้กำกับการ"}],
-    "ผกก.ภ.": [{ORTH: "ผกก.ภ.", LEMMA: "ผู้กำกับการตำรวจภูธร"}],
-    "ผจก.": [{ORTH: "ผจก.", LEMMA: "ผู้จัดการ"}],
-    "ผช.": [{ORTH: "ผช.", LEMMA: "ผู้ช่วย"}],
-    "ผชก.": [{ORTH: "ผชก.", LEMMA: "ผู้ชำนาญการ"}],
-    "ผช.ผอ.": [{ORTH: "ผช.ผอ.", LEMMA: "ผู้ช่วยผู้อำนวยการ"}],
-    "ผญบ.": [{ORTH: "ผญบ.", LEMMA: "ผู้ใหญ่บ้าน"}],
-    "ผบ.": [{ORTH: "ผบ.", LEMMA: "ผู้บังคับบัญชา"}],
-    "ผบก.": [{ORTH: "ผบก.", LEMMA: "ผู้บังคับบัญชาการ (ตำรวจ)"}],
-    "ผบก.น.": [{ORTH: "ผบก.น.", LEMMA: "ผู้บังคับการตำรวจนครบาล"}],
-    "ผบก.ป.": [{ORTH: "ผบก.ป.", LEMMA: "ผู้บังคับการตำรวจกองปราบปราม"}],
-    "ผบก.ปค.": [
-        {
-            ORTH: "ผบก.ปค.",
-            LEMMA: "ผู้บังคับการ กองบังคับการปกครอง (โรงเรียนนายร้อยตำรวจ)",
-        }
-    ],
-    "ผบก.ปม.": [{ORTH: "ผบก.ปม.", LEMMA: "ผู้บังคับการตำรวจป่าไม้"}],
-    "ผบก.ภ.": [{ORTH: "ผบก.ภ.", LEMMA: "ผู้บังคับการตำรวจภูธร"}],
-    "ผบช.": [{ORTH: "ผบช.", LEMMA: "ผู้บัญชาการ (ตำรวจ)"}],
-    "ผบช.ก.": [{ORTH: "ผบช.ก.", LEMMA: "ผู้บัญชาการตำรวจสอบสวนกลาง"}],
-    "ผบช.ตชด.": [{ORTH: "ผบช.ตชด.", LEMMA: "ผู้บัญชาการตำรวจตระเวนชายแดน"}],
-    "ผบช.น.": [{ORTH: "ผบช.น.", LEMMA: "ผู้บัญชาการตำรวจนครบาล"}],
-    "ผบช.ภ.": [{ORTH: "ผบช.ภ.", LEMMA: "ผู้บัญชาการตำรวจภูธร"}],
-    "ผบ.ทบ.": [{ORTH: "ผบ.ทบ.", LEMMA: "ผู้บัญชาการทหารบก"}],
-    "ผบ.ตร.": [{ORTH: "ผบ.ตร.", LEMMA: "ผู้บัญชาการตำรวจแห่งชาติ"}],
-    "ผบ.ทร.": [{ORTH: "ผบ.ทร.", LEMMA: "ผู้บัญชาการทหารเรือ"}],
-    "ผบ.ทอ.": [{ORTH: "ผบ.ทอ.", LEMMA: "ผู้บัญชาการทหารอากาศ"}],
-    "ผบ.ทสส.": [{ORTH: "ผบ.ทสส.", LEMMA: "ผู้บัญชาการทหารสูงสุด"}],
-    "ผวจ.": [{ORTH: "ผวจ.", LEMMA: "ผู้ว่าราชการจังหวัด"}],
-    "ผู้ว่าฯ": [{ORTH: "ผู้ว่าฯ", LEMMA: "ผู้ว่าราชการจังหวัด"}],
-    "พ.จ.ต.": [{ORTH: "พ.จ.ต.", LEMMA: "พันจ่าตรี"}],
-    "พ.จ.ท.": [{ORTH: "พ.จ.ท.", LEMMA: "พันจ่าโท"}],
-    "พ.จ.อ.": [{ORTH: "พ.จ.อ.", LEMMA: "พันจ่าเอก"}],
-    "พญ.": [{ORTH: "พญ.", LEMMA: "แพทย์หญิง"}],
-    "ฯพณฯ": [{ORTH: "ฯพณฯ", LEMMA: "พณท่าน"}],
-    "พ.ต.": [{ORTH: "พ.ต.", LEMMA: "พันตรี"}],
-    "พ.ท.": [{ORTH: "พ.ท.", LEMMA: "พันโท"}],
-    "พ.อ.": [{ORTH: "พ.อ.", LEMMA: "พันเอก"}],
-    "พ.ต.อ.พิเศษ": [{ORTH: "พ.ต.อ.พิเศษ", LEMMA: "พันตำรวจเอกพิเศษ"}],
-    "พลฯ": [{ORTH: "พลฯ", LEMMA: "พลทหาร"}],
-    "พล.๑ รอ.": [{ORTH: "พล.๑ รอ.", LEMMA: "กองพลที่ ๑ รักษาพระองค์ กองทัพบก"}],
-    "พล.ต.": [{ORTH: "พล.ต.", LEMMA: "พลตรี"}],
-    "พล.ต.ต.": [{ORTH: "พล.ต.ต.", LEMMA: "พลตำรวจตรี"}],
-    "พล.ต.ท.": [{ORTH: "พล.ต.ท.", LEMMA: "พลตำรวจโท"}],
-    "พล.ต.อ.": [{ORTH: "พล.ต.อ.", LEMMA: "พลตำรวจเอก"}],
-    "พล.ท.": [{ORTH: "พล.ท.", LEMMA: "พลโท"}],
-    "พล.ปตอ.": [{ORTH: "พล.ปตอ.", LEMMA: "กองพลทหารปืนใหญ่ต่อสู่อากาศยาน"}],
-    "พล.ม.": [{ORTH: "พล.ม.", LEMMA: "กองพลทหารม้า"}],
-    "พล.ม.๒": [{ORTH: "พล.ม.๒", LEMMA: "กองพลทหารม้าที่ ๒"}],
-    "พล.ร.ต.": [{ORTH: "พล.ร.ต.", LEMMA: "พลเรือตรี"}],
-    "พล.ร.ท.": [{ORTH: "พล.ร.ท.", LEMMA: "พลเรือโท"}],
-    "พล.ร.อ.": [{ORTH: "พล.ร.อ.", LEMMA: "พลเรือเอก"}],
-    "พล.อ.": [{ORTH: "พล.อ.", LEMMA: "พลเอก"}],
-    "พล.อ.ต.": [{ORTH: "พล.อ.ต.", LEMMA: "พลอากาศตรี"}],
-    "พล.อ.ท.": [{ORTH: "พล.อ.ท.", LEMMA: "พลอากาศโท"}],
-    "พล.อ.อ.": [{ORTH: "พล.อ.อ.", LEMMA: "พลอากาศเอก"}],
-    "พ.อ.พิเศษ": [{ORTH: "พ.อ.พิเศษ", LEMMA: "พันเอกพิเศษ"}],
-    "พ.อ.ต.": [{ORTH: "พ.อ.ต.", LEMMA: "พันจ่าอากาศตรี"}],
-    "พ.อ.ท.": [{ORTH: "พ.อ.ท.", LEMMA: "พันจ่าอากาศโท"}],
-    "พ.อ.อ.": [{ORTH: "พ.อ.อ.", LEMMA: "พันจ่าอากาศเอก"}],
-    "ภกญ.": [{ORTH: "ภกญ.", LEMMA: "เภสัชกรหญิง"}],
-    "ม.จ.": [{ORTH: "ม.จ.", LEMMA: "หม่อมเจ้า"}],
-    "มท1": [{ORTH: "มท1", LEMMA: "รัฐมนตรีว่าการกระทรวงมหาดไทย"}],
-    "ม.ร.ว.": [{ORTH: "ม.ร.ว.", LEMMA: "หม่อมราชวงศ์"}],
-    "มล.": [{ORTH: "มล.", LEMMA: "หม่อมหลวง"}],
-    "ร.ต.": [{ORTH: "ร.ต.", LEMMA: "ร้อยตรี,เรือตรี,เรืออากาศตรี"}],
-    "ร.ต.ต.": [{ORTH: "ร.ต.ต.", LEMMA: "ร้อยตำรวจตรี"}],
-    "ร.ต.ท.": [{ORTH: "ร.ต.ท.", LEMMA: "ร้อยตำรวจโท"}],
-    "ร.ต.อ.": [{ORTH: "ร.ต.อ.", LEMMA: "ร้อยตำรวจเอก"}],
-    "ร.ท.": [{ORTH: "ร.ท.", LEMMA: "ร้อยโท,เรือโท,เรืออากาศโท"}],
-    "รมช.": [{ORTH: "รมช.", LEMMA: "รัฐมนตรีช่วยว่าการกระทรวง"}],
-    "รมต.": [{ORTH: "รมต.", LEMMA: "รัฐมนตรี"}],
-    "รมว.": [{ORTH: "รมว.", LEMMA: "รัฐมนตรีว่าการกระทรวง"}],
-    "รศ.": [{ORTH: "รศ.", LEMMA: "รองศาสตราจารย์"}],
-    "ร.อ.": [{ORTH: "ร.อ.", LEMMA: "ร้อยเอก,เรือเอก,เรืออากาศเอก"}],
-    "ศ.": [{ORTH: "ศ.", LEMMA: "ศาสตราจารย์"}],
-    "ส.ต.": [{ORTH: "ส.ต.", LEMMA: "สิบตรี"}],
-    "ส.ต.ต.": [{ORTH: "ส.ต.ต.", LEMMA: "สิบตำรวจตรี"}],
-    "ส.ต.ท.": [{ORTH: "ส.ต.ท.", LEMMA: "สิบตำรวจโท"}],
-    "ส.ต.อ.": [{ORTH: "ส.ต.อ.", LEMMA: "สิบตำรวจเอก"}],
-    "ส.ท.": [{ORTH: "ส.ท.", LEMMA: "สิบโท"}],
-    "สพ.": [{ORTH: "สพ.", LEMMA: "สัตวแพทย์"}],
-    "สพ.ญ.": [{ORTH: "สพ.ญ.", LEMMA: "สัตวแพทย์หญิง"}],
-    "สพ.ช.": [{ORTH: "สพ.ช.", LEMMA: "สัตวแพทย์ชาย"}],
-    "ส.อ.": [{ORTH: "ส.อ.", LEMMA: "สิบเอก"}],
-    "อจ.": [{ORTH: "อจ.", LEMMA: "อาจารย์"}],
-    "อจญ.": [{ORTH: "อจญ.", LEMMA: "อาจารย์ใหญ่"}],
+    "ดร.": [{ORTH: "ดร."}],
+    "ด.ต.": [{ORTH: "ด.ต."}],
+    "จ.ต.": [{ORTH: "จ.ต."}],
+    "จ.ท.": [{ORTH: "จ.ท."}],
+    "จ.ส.ต.": [{ORTH: "จ.ส.ต."}],
+    "จสต.": [{ORTH: "จสต."}],
+    "จ.ส.ท.": [{ORTH: "จ.ส.ท."}],
+    "จ.ส.อ.": [{ORTH: "จ.ส.อ."}],
+    "จ.อ.": [{ORTH: "จ.อ."}],
+    "ทพญ.": [{ORTH: "ทพญ."}],
+    "ทนพ.": [{ORTH: "ทนพ."}],
+    "นจอ.": [{ORTH: "นจอ."}],
+    "น.ช.": [{ORTH: "น.ช."}],
+    "น.ญ.": [{ORTH: "น.ญ."}],
+    "น.ต.": [{ORTH: "น.ต."}],
+    "น.ท.": [{ORTH: "น.ท."}],
+    "นตท.": [{ORTH: "นตท."}],
+    "นนส.": [{ORTH: "นนส."}],
+    "นนร.": [{ORTH: "นนร."}],
+    "นนอ.": [{ORTH: "นนอ."}],
+    "นพ.": [{ORTH: "นพ."}],
+    "นพท.": [{ORTH: "นพท."}],
+    "นรจ.": [{ORTH: "นรจ."}],
+    "นรต.": [{ORTH: "นรต."}],
+    "นศพ.": [{ORTH: "นศพ."}],
+    "นศท.": [{ORTH: "นศท."}],
+    "น.สพ.": [{ORTH: "น.สพ."}],
+    "น.อ.": [{ORTH: "น.อ."}],
+    "บช.ก.": [{ORTH: "บช.ก."}],
+    "บช.น.": [{ORTH: "บช.น."}],
+    "ผกก.": [{ORTH: "ผกก."}],
+    "ผกก.ภ.": [{ORTH: "ผกก.ภ."}],
+    "ผจก.": [{ORTH: "ผจก."}],
+    "ผช.": [{ORTH: "ผช."}],
+    "ผชก.": [{ORTH: "ผชก."}],
+    "ผช.ผอ.": [{ORTH: "ผช.ผอ."}],
+    "ผญบ.": [{ORTH: "ผญบ."}],
+    "ผบ.": [{ORTH: "ผบ."}],
+    "ผบก.": [{ORTH: "ผบก."}],
+    "ผบก.น.": [{ORTH: "ผบก.น."}],
+    "ผบก.ป.": [{ORTH: "ผบก.ป."}],
+    "ผบก.ปค.": [{ORTH: "ผบก.ปค."}],
+    "ผบก.ปม.": [{ORTH: "ผบก.ปม."}],
+    "ผบก.ภ.": [{ORTH: "ผบก.ภ."}],
+    "ผบช.": [{ORTH: "ผบช."}],
+    "ผบช.ก.": [{ORTH: "ผบช.ก."}],
+    "ผบช.ตชด.": [{ORTH: "ผบช.ตชด."}],
+    "ผบช.น.": [{ORTH: "ผบช.น."}],
+    "ผบช.ภ.": [{ORTH: "ผบช.ภ."}],
+    "ผบ.ทบ.": [{ORTH: "ผบ.ทบ."}],
+    "ผบ.ตร.": [{ORTH: "ผบ.ตร."}],
+    "ผบ.ทร.": [{ORTH: "ผบ.ทร."}],
+    "ผบ.ทอ.": [{ORTH: "ผบ.ทอ."}],
+    "ผบ.ทสส.": [{ORTH: "ผบ.ทสส."}],
+    "ผวจ.": [{ORTH: "ผวจ."}],
+    "ผู้ว่าฯ": [{ORTH: "ผู้ว่าฯ"}],
+    "พ.จ.ต.": [{ORTH: "พ.จ.ต."}],
+    "พ.จ.ท.": [{ORTH: "พ.จ.ท."}],
+    "พ.จ.อ.": [{ORTH: "พ.จ.อ."}],
+    "พญ.": [{ORTH: "พญ."}],
+    "ฯพณฯ": [{ORTH: "ฯพณฯ"}],
+    "พ.ต.": [{ORTH: "พ.ต."}],
+    "พ.ท.": [{ORTH: "พ.ท."}],
+    "พ.อ.": [{ORTH: "พ.อ."}],
+    "พ.ต.อ.พิเศษ": [{ORTH: "พ.ต.อ.พิเศษ"}],
+    "พลฯ": [{ORTH: "พลฯ"}],
+    "พล.๑ รอ.": [{ORTH: "พล.๑ รอ."}],
+    "พล.ต.": [{ORTH: "พล.ต."}],
+    "พล.ต.ต.": [{ORTH: "พล.ต.ต."}],
+    "พล.ต.ท.": [{ORTH: "พล.ต.ท."}],
+    "พล.ต.อ.": [{ORTH: "พล.ต.อ."}],
+    "พล.ท.": [{ORTH: "พล.ท."}],
+    "พล.ปตอ.": [{ORTH: "พล.ปตอ."}],
+    "พล.ม.": [{ORTH: "พล.ม."}],
+    "พล.ม.๒": [{ORTH: "พล.ม.๒"}],
+    "พล.ร.ต.": [{ORTH: "พล.ร.ต."}],
+    "พล.ร.ท.": [{ORTH: "พล.ร.ท."}],
+    "พล.ร.อ.": [{ORTH: "พล.ร.อ."}],
+    "พล.อ.": [{ORTH: "พล.อ."}],
+    "พล.อ.ต.": [{ORTH: "พล.อ.ต."}],
+    "พล.อ.ท.": [{ORTH: "พล.อ.ท."}],
+    "พล.อ.อ.": [{ORTH: "พล.อ.อ."}],
+    "พ.อ.พิเศษ": [{ORTH: "พ.อ.พิเศษ"}],
+    "พ.อ.ต.": [{ORTH: "พ.อ.ต."}],
+    "พ.อ.ท.": [{ORTH: "พ.อ.ท."}],
+    "พ.อ.อ.": [{ORTH: "พ.อ.อ."}],
+    "ภกญ.": [{ORTH: "ภกญ."}],
+    "ม.จ.": [{ORTH: "ม.จ."}],
+    "มท1": [{ORTH: "มท1"}],
+    "ม.ร.ว.": [{ORTH: "ม.ร.ว."}],
+    "มล.": [{ORTH: "มล."}],
+    "ร.ต.": [{ORTH: "ร.ต."}],
+    "ร.ต.ต.": [{ORTH: "ร.ต.ต."}],
+    "ร.ต.ท.": [{ORTH: "ร.ต.ท."}],
+    "ร.ต.อ.": [{ORTH: "ร.ต.อ."}],
+    "ร.ท.": [{ORTH: "ร.ท."}],
+    "รมช.": [{ORTH: "รมช."}],
+    "รมต.": [{ORTH: "รมต."}],
+    "รมว.": [{ORTH: "รมว."}],
+    "รศ.": [{ORTH: "รศ."}],
+    "ร.อ.": [{ORTH: "ร.อ."}],
+    "ศ.": [{ORTH: "ศ."}],
+    "ส.ต.": [{ORTH: "ส.ต."}],
+    "ส.ต.ต.": [{ORTH: "ส.ต.ต."}],
+    "ส.ต.ท.": [{ORTH: "ส.ต.ท."}],
+    "ส.ต.อ.": [{ORTH: "ส.ต.อ."}],
+    "ส.ท.": [{ORTH: "ส.ท."}],
+    "สพ.": [{ORTH: "สพ."}],
+    "สพ.ญ.": [{ORTH: "สพ.ญ."}],
+    "สพ.ช.": [{ORTH: "สพ.ช."}],
+    "ส.อ.": [{ORTH: "ส.อ."}],
+    "อจ.": [{ORTH: "อจ."}],
+    "อจญ.": [{ORTH: "อจญ."}],
     # วุฒิ / bachelor degree
-    "ป.": [{ORTH: "ป.", LEMMA: "ประถมศึกษา"}],
-    "ป.กศ.": [{ORTH: "ป.กศ.", LEMMA: "ประกาศนียบัตรวิชาการศึกษา"}],
-    "ป.กศ.สูง": [{ORTH: "ป.กศ.สูง", LEMMA: "ประกาศนียบัตรวิชาการศึกษาชั้นสูง"}],
-    "ปวช.": [{ORTH: "ปวช.", LEMMA: "ประกาศนียบัตรวิชาชีพ"}],
-    "ปวท.": [{ORTH: "ปวท.", LEMMA: "ประกาศนียบัตรวิชาชีพเทคนิค"}],
-    "ปวส.": [{ORTH: "ปวส.", LEMMA: "ประกาศนียบัตรวิชาชีพชั้นสูง"}],
-    "ปทส.": [{ORTH: "ปทส.", LEMMA: "ประกาศนียบัตรครูเทคนิคชั้นสูง"}],
-    "กษ.บ.": [{ORTH: "กษ.บ.", LEMMA: "เกษตรศาสตรบัณฑิต"}],
-    "กษ.ม.": [{ORTH: "กษ.ม.", LEMMA: "เกษตรศาสตรมหาบัณฑิต"}],
-    "กษ.ด.": [{ORTH: "กษ.ด.", LEMMA: "เกษตรศาสตรดุษฎีบัณฑิต"}],
-    "ค.บ.": [{ORTH: "ค.บ.", LEMMA: "ครุศาสตรบัณฑิต"}],
-    "คศ.บ.": [{ORTH: "คศ.บ.", LEMMA: "คหกรรมศาสตรบัณฑิต"}],
-    "คศ.ม.": [{ORTH: "คศ.ม.", LEMMA: "คหกรรมศาสตรมหาบัณฑิต"}],
-    "คศ.ด.": [{ORTH: "คศ.ด.", LEMMA: "คหกรรมศาสตรดุษฎีบัณฑิต"}],
-    "ค.อ.บ.": [{ORTH: "ค.อ.บ.", LEMMA: "ครุศาสตรอุตสาหกรรมบัณฑิต"}],
-    "ค.อ.ม.": [{ORTH: "ค.อ.ม.", LEMMA: "ครุศาสตรอุตสาหกรรมมหาบัณฑิต"}],
-    "ค.อ.ด.": [{ORTH: "ค.อ.ด.", LEMMA: "ครุศาสตรอุตสาหกรรมดุษฎีบัณฑิต"}],
-    "ทก.บ.": [{ORTH: "ทก.บ.", LEMMA: "เทคโนโลยีการเกษตรบัณฑิต"}],
-    "ทก.ม.": [{ORTH: "ทก.ม.", LEMMA: "เทคโนโลยีการเกษตรมหาบัณฑิต"}],
-    "ทก.ด.": [{ORTH: "ทก.ด.", LEMMA: "เทคโนโลยีการเกษตรดุษฎีบัณฑิต"}],
-    "ท.บ.": [{ORTH: "ท.บ.", LEMMA: "ทันตแพทยศาสตรบัณฑิต"}],
-    "ท.ม.": [{ORTH: "ท.ม.", LEMMA: "ทันตแพทยศาสตรมหาบัณฑิต"}],
-    "ท.ด.": [{ORTH: "ท.ด.", LEMMA: "ทันตแพทยศาสตรดุษฎีบัณฑิต"}],
-    "น.บ.": [{ORTH: "น.บ.", LEMMA: "นิติศาสตรบัณฑิต"}],
-    "น.ม.": [{ORTH: "น.ม.", LEMMA: "นิติศาสตรมหาบัณฑิต"}],
-    "น.ด.": [{ORTH: "น.ด.", LEMMA: "นิติศาสตรดุษฎีบัณฑิต"}],
-    "นศ.บ.": [{ORTH: "นศ.บ.", LEMMA: "นิเทศศาสตรบัณฑิต"}],
-    "นศ.ม.": [{ORTH: "นศ.ม.", LEMMA: "นิเทศศาสตรมหาบัณฑิต"}],
-    "นศ.ด.": [{ORTH: "นศ.ด.", LEMMA: "นิเทศศาสตรดุษฎีบัณฑิต"}],
-    "บช.บ.": [{ORTH: "บช.บ.", LEMMA: "บัญชีบัณฑิต"}],
-    "บช.ม.": [{ORTH: "บช.ม.", LEMMA: "บัญชีมหาบัณฑิต"}],
-    "บช.ด.": [{ORTH: "บช.ด.", LEMMA: "บัญชีดุษฎีบัณฑิต"}],
-    "บธ.บ.": [{ORTH: "บธ.บ.", LEMMA: "บริหารธุรกิจบัณฑิต"}],
-    "บธ.ม.": [{ORTH: "บธ.ม.", LEMMA: "บริหารธุรกิจมหาบัณฑิต"}],
-    "บธ.ด.": [{ORTH: "บธ.ด.", LEMMA: "บริหารธุรกิจดุษฎีบัณฑิต"}],
-    "พณ.บ.": [{ORTH: "พณ.บ.", LEMMA: "พาณิชยศาสตรบัณฑิต"}],
-    "พณ.ม.": [{ORTH: "พณ.ม.", LEMMA: "พาณิชยศาสตรมหาบัณฑิต"}],
-    "พณ.ด.": [{ORTH: "พณ.ด.", LEMMA: "พาณิชยศาสตรดุษฎีบัณฑิต"}],
-    "พ.บ.": [{ORTH: "พ.บ.", LEMMA: "แพทยศาสตรบัณฑิต"}],
-    "พ.ม.": [{ORTH: "พ.ม.", LEMMA: "แพทยศาสตรมหาบัณฑิต"}],
-    "พ.ด.": [{ORTH: "พ.ด.", LEMMA: "แพทยศาสตรดุษฎีบัณฑิต"}],
-    "พธ.บ.": [{ORTH: "พธ.บ.", LEMMA: "พุทธศาสตรบัณฑิต"}],
-    "พธ.ม.": [{ORTH: "พธ.ม.", LEMMA: "พุทธศาสตรมหาบัณฑิต"}],
-    "พธ.ด.": [{ORTH: "พธ.ด.", LEMMA: "พุทธศาสตรดุษฎีบัณฑิต"}],
-    "พบ.บ.": [{ORTH: "พบ.บ.", LEMMA: "พัฒนบริหารศาสตรบัณฑิต"}],
-    "พบ.ม.": [{ORTH: "พบ.ม.", LEMMA: "พัฒนบริหารศาสตรมหาบัณฑิต"}],
-    "พบ.ด.": [{ORTH: "พบ.ด.", LEMMA: "พัฒนบริหารศาสตรดุษฎีบัณฑิต"}],
-    "พย.บ.": [{ORTH: "พย.บ.", LEMMA: "พยาบาลศาสตรดุษฎีบัณฑิต"}],
-    "พย.ม.": [{ORTH: "พย.ม.", LEMMA: "พยาบาลศาสตรมหาบัณฑิต"}],
-    "พย.ด.": [{ORTH: "พย.ด.", LEMMA: "พยาบาลศาสตรดุษฎีบัณฑิต"}],
-    "พศ.บ.": [{ORTH: "พศ.บ.", LEMMA: "พาณิชยศาสตรบัณฑิต"}],
-    "พศ.ม.": [{ORTH: "พศ.ม.", LEMMA: "พาณิชยศาสตรมหาบัณฑิต"}],
-    "พศ.ด.": [{ORTH: "พศ.ด.", LEMMA: "พาณิชยศาสตรดุษฎีบัณฑิต"}],
-    "ภ.บ.": [{ORTH: "ภ.บ.", LEMMA: "เภสัชศาสตรบัณฑิต"}],
-    "ภ.ม.": [{ORTH: "ภ.ม.", LEMMA: "เภสัชศาสตรมหาบัณฑิต"}],
-    "ภ.ด.": [{ORTH: "ภ.ด.", LEMMA: "เภสัชศาสตรดุษฎีบัณฑิต"}],
-    "ภ.สถ.บ.": [{ORTH: "ภ.สถ.บ.", LEMMA: "ภูมิสถาปัตยกรรมศาสตรบัณฑิต"}],
-    "รป.บ.": [{ORTH: "รป.บ.", LEMMA: "รัฐประศาสนศาสตร์บัณฑิต"}],
-    "รป.ม.": [{ORTH: "รป.ม.", LEMMA: "รัฐประศาสนศาสตร์มหาบัณฑิต"}],
-    "วท.บ.": [{ORTH: "วท.บ.", LEMMA: "วิทยาศาสตรบัณฑิต"}],
-    "วท.ม.": [{ORTH: "วท.ม.", LEMMA: "วิทยาศาสตรมหาบัณฑิต"}],
-    "วท.ด.": [{ORTH: "วท.ด.", LEMMA: "วิทยาศาสตรดุษฎีบัณฑิต"}],
-    "ศ.บ.": [{ORTH: "ศ.บ.", LEMMA: "ศิลปบัณฑิต"}],
-    "ศศ.บ.": [{ORTH: "ศศ.บ.", LEMMA: "ศิลปศาสตรบัณฑิต"}],
-    "ศษ.บ.": [{ORTH: "ศษ.บ.", LEMMA: "ศึกษาศาสตรบัณฑิต"}],
-    "ศส.บ.": [{ORTH: "ศส.บ.", LEMMA: "เศรษฐศาสตรบัณฑิต"}],
-    "สถ.บ.": [{ORTH: "สถ.บ.", LEMMA: "สถาปัตยกรรมศาสตรบัณฑิต"}],
-    "สถ.ม.": [{ORTH: "สถ.ม.", LEMMA: "สถาปัตยกรรมศาสตรมหาบัณฑิต"}],
-    "สถ.ด.": [{ORTH: "สถ.ด.", LEMMA: "สถาปัตยกรรมศาสตรดุษฎีบัณฑิต"}],
-    "สพ.บ.": [{ORTH: "สพ.บ.", LEMMA: "สัตวแพทยศาสตรบัณฑิต"}],
-    "อ.บ.": [{ORTH: "อ.บ.", LEMMA: "อักษรศาสตรบัณฑิต"}],
-    "อ.ม.": [{ORTH: "อ.ม.", LEMMA: "อักษรศาสตรมหาบัณฑิต"}],
-    "อ.ด.": [{ORTH: "อ.ด.", LEMMA: "อักษรศาสตรดุษฎีบัณฑิต"}],
+    "ป.": [{ORTH: "ป."}],
+    "ป.กศ.": [{ORTH: "ป.กศ."}],
+    "ป.กศ.สูง": [{ORTH: "ป.กศ.สูง"}],
+    "ปวช.": [{ORTH: "ปวช."}],
+    "ปวท.": [{ORTH: "ปวท."}],
+    "ปวส.": [{ORTH: "ปวส."}],
+    "ปทส.": [{ORTH: "ปทส."}],
+    "กษ.บ.": [{ORTH: "กษ.บ."}],
+    "กษ.ม.": [{ORTH: "กษ.ม."}],
+    "กษ.ด.": [{ORTH: "กษ.ด."}],
+    "ค.บ.": [{ORTH: "ค.บ."}],
+    "คศ.บ.": [{ORTH: "คศ.บ."}],
+    "คศ.ม.": [{ORTH: "คศ.ม."}],
+    "คศ.ด.": [{ORTH: "คศ.ด."}],
+    "ค.อ.บ.": [{ORTH: "ค.อ.บ."}],
+    "ค.อ.ม.": [{ORTH: "ค.อ.ม."}],
+    "ค.อ.ด.": [{ORTH: "ค.อ.ด."}],
+    "ทก.บ.": [{ORTH: "ทก.บ."}],
+    "ทก.ม.": [{ORTH: "ทก.ม."}],
+    "ทก.ด.": [{ORTH: "ทก.ด."}],
+    "ท.บ.": [{ORTH: "ท.บ."}],
+    "ท.ม.": [{ORTH: "ท.ม."}],
+    "ท.ด.": [{ORTH: "ท.ด."}],
+    "น.บ.": [{ORTH: "น.บ."}],
+    "น.ม.": [{ORTH: "น.ม."}],
+    "น.ด.": [{ORTH: "น.ด."}],
+    "นศ.บ.": [{ORTH: "นศ.บ."}],
+    "นศ.ม.": [{ORTH: "นศ.ม."}],
+    "นศ.ด.": [{ORTH: "นศ.ด."}],
+    "บช.บ.": [{ORTH: "บช.บ."}],
+    "บช.ม.": [{ORTH: "บช.ม."}],
+    "บช.ด.": [{ORTH: "บช.ด."}],
+    "บธ.บ.": [{ORTH: "บธ.บ."}],
+    "บธ.ม.": [{ORTH: "บธ.ม."}],
+    "บธ.ด.": [{ORTH: "บธ.ด."}],
+    "พณ.บ.": [{ORTH: "พณ.บ."}],
+    "พณ.ม.": [{ORTH: "พณ.ม."}],
+    "พณ.ด.": [{ORTH: "พณ.ด."}],
+    "พ.บ.": [{ORTH: "พ.บ."}],
+    "พ.ม.": [{ORTH: "พ.ม."}],
+    "พ.ด.": [{ORTH: "พ.ด."}],
+    "พธ.บ.": [{ORTH: "พธ.บ."}],
+    "พธ.ม.": [{ORTH: "พธ.ม."}],
+    "พธ.ด.": [{ORTH: "พธ.ด."}],
+    "พบ.บ.": [{ORTH: "พบ.บ."}],
+    "พบ.ม.": [{ORTH: "พบ.ม."}],
+    "พบ.ด.": [{ORTH: "พบ.ด."}],
+    "พย.บ.": [{ORTH: "พย.บ."}],
+    "พย.ม.": [{ORTH: "พย.ม."}],
+    "พย.ด.": [{ORTH: "พย.ด."}],
+    "พศ.บ.": [{ORTH: "พศ.บ."}],
+    "พศ.ม.": [{ORTH: "พศ.ม."}],
+    "พศ.ด.": [{ORTH: "พศ.ด."}],
+    "ภ.บ.": [{ORTH: "ภ.บ."}],
+    "ภ.ม.": [{ORTH: "ภ.ม."}],
+    "ภ.ด.": [{ORTH: "ภ.ด."}],
+    "ภ.สถ.บ.": [{ORTH: "ภ.สถ.บ."}],
+    "รป.บ.": [{ORTH: "รป.บ."}],
+    "รป.ม.": [{ORTH: "รป.ม."}],
+    "วท.บ.": [{ORTH: "วท.บ."}],
+    "วท.ม.": [{ORTH: "วท.ม."}],
+    "วท.ด.": [{ORTH: "วท.ด."}],
+    "ศ.บ.": [{ORTH: "ศ.บ."}],
+    "ศศ.บ.": [{ORTH: "ศศ.บ."}],
+    "ศษ.บ.": [{ORTH: "ศษ.บ."}],
+    "ศส.บ.": [{ORTH: "ศส.บ."}],
+    "สถ.บ.": [{ORTH: "สถ.บ."}],
+    "สถ.ม.": [{ORTH: "สถ.ม."}],
+    "สถ.ด.": [{ORTH: "สถ.ด."}],
+    "สพ.บ.": [{ORTH: "สพ.บ."}],
+    "อ.บ.": [{ORTH: "อ.บ."}],
+    "อ.ม.": [{ORTH: "อ.ม."}],
+    "อ.ด.": [{ORTH: "อ.ด."}],
     # ปี / เวลา / year / time
-    "ชม.": [{ORTH: "ชม.", LEMMA: "ชั่วโมง"}],
-    "จ.ศ.": [{ORTH: "จ.ศ.", LEMMA: "จุลศักราช"}],
-    "ค.ศ.": [{ORTH: "ค.ศ.", LEMMA: "คริสต์ศักราช"}],
-    "ฮ.ศ.": [{ORTH: "ฮ.ศ.", LEMMA: "ฮิจเราะห์ศักราช"}],
-    "ว.ด.ป.": [{ORTH: "ว.ด.ป.", LEMMA: "วัน เดือน ปี"}],
+    "ชม.": [{ORTH: "ชม."}],
+    "จ.ศ.": [{ORTH: "จ.ศ."}],
+    "ค.ศ.": [{ORTH: "ค.ศ."}],
+    "ฮ.ศ.": [{ORTH: "ฮ.ศ."}],
+    "ว.ด.ป.": [{ORTH: "ว.ด.ป."}],
     # ระยะทาง / distance
-    "ฮม.": [{ORTH: "ฮม.", LEMMA: "เฮกโตเมตร"}],
-    "ดคม.": [{ORTH: "ดคม.", LEMMA: "เดคาเมตร"}],
-    "ดม.": [{ORTH: "ดม.", LEMMA: "เดซิเมตร"}],
-    "มม.": [{ORTH: "มม.", LEMMA: "มิลลิเมตร"}],
-    "ซม.": [{ORTH: "ซม.", LEMMA: "เซนติเมตร"}],
-    "กม.": [{ORTH: "กม.", LEMMA: "กิโลเมตร"}],
+    "ฮม.": [{ORTH: "ฮม."}],
+    "ดคม.": [{ORTH: "ดคม."}],
+    "ดม.": [{ORTH: "ดม."}],
+    "มม.": [{ORTH: "มม."}],
+    "ซม.": [{ORTH: "ซม."}],
+    "กม.": [{ORTH: "กม."}],
     # น้ำหนัก / weight
-    "น.น.": [{ORTH: "น.น.", LEMMA: "น้ำหนัก"}],
-    "ฮก.": [{ORTH: "ฮก.", LEMMA: "เฮกโตกรัม"}],
-    "ดคก.": [{ORTH: "ดคก.", LEMMA: "เดคากรัม"}],
-    "ดก.": [{ORTH: "ดก.", LEMMA: "เดซิกรัม"}],
-    "ซก.": [{ORTH: "ซก.", LEMMA: "เซนติกรัม"}],
-    "มก.": [{ORTH: "มก.", LEMMA: "มิลลิกรัม"}],
-    "ก.": [{ORTH: "ก.", LEMMA: "กรัม"}],
-    "กก.": [{ORTH: "กก.", LEMMA: "กิโลกรัม"}],
+    "น.น.": [{ORTH: "น.น."}],
+    "ฮก.": [{ORTH: "ฮก."}],
+    "ดคก.": [{ORTH: "ดคก."}],
+    "ดก.": [{ORTH: "ดก."}],
+    "ซก.": [{ORTH: "ซก."}],
+    "มก.": [{ORTH: "มก."}],
+    "ก.": [{ORTH: "ก."}],
+    "กก.": [{ORTH: "กก."}],
     # ปริมาตร / volume
-    "ฮล.": [{ORTH: "ฮล.", LEMMA: "เฮกโตลิตร"}],
-    "ดคล.": [{ORTH: "ดคล.", LEMMA: "เดคาลิตร"}],
-    "ดล.": [{ORTH: "ดล.", LEMMA: "เดซิลิตร"}],
-    "ซล.": [{ORTH: "ซล.", LEMMA: "เซนติลิตร"}],
-    "ล.": [{ORTH: "ล.", LEMMA: "ลิตร"}],
-    "กล.": [{ORTH: "กล.", LEMMA: "กิโลลิตร"}],
-    "ลบ.": [{ORTH: "ลบ.", LEMMA: "ลูกบาศก์"}],
+    "ฮล.": [{ORTH: "ฮล."}],
+    "ดคล.": [{ORTH: "ดคล."}],
+    "ดล.": [{ORTH: "ดล."}],
+    "ซล.": [{ORTH: "ซล."}],
+    "ล.": [{ORTH: "ล."}],
+    "กล.": [{ORTH: "กล."}],
+    "ลบ.": [{ORTH: "ลบ."}],
     # พื้นที่ / area
-    "ตร.ซม.": [{ORTH: "ตร.ซม.", LEMMA: "ตารางเซนติเมตร"}],
-    "ตร.ม.": [{ORTH: "ตร.ม.", LEMMA: "ตารางเมตร"}],
-    "ตร.ว.": [{ORTH: "ตร.ว.", LEMMA: "ตารางวา"}],
-    "ตร.กม.": [{ORTH: "ตร.กม.", LEMMA: "ตารางกิโลเมตร"}],
+    "ตร.ซม.": [{ORTH: "ตร.ซม."}],
+    "ตร.ม.": [{ORTH: "ตร.ม."}],
+    "ตร.ว.": [{ORTH: "ตร.ว."}],
+    "ตร.กม.": [{ORTH: "ตร.กม."}],
     # เดือน / month
-    "ม.ค.": [{ORTH: "ม.ค.", LEMMA: "มกราคม"}],
-    "ก.พ.": [{ORTH: "ก.พ.", LEMMA: "กุมภาพันธ์"}],
-    "มี.ค.": [{ORTH: "มี.ค.", LEMMA: "มีนาคม"}],
-    "เม.ย.": [{ORTH: "เม.ย.", LEMMA: "เมษายน"}],
-    "พ.ค.": [{ORTH: "พ.ค.", LEMMA: "พฤษภาคม"}],
-    "มิ.ย.": [{ORTH: "มิ.ย.", LEMMA: "มิถุนายน"}],
-    "ก.ค.": [{ORTH: "ก.ค.", LEMMA: "กรกฎาคม"}],
-    "ส.ค.": [{ORTH: "ส.ค.", LEMMA: "สิงหาคม"}],
-    "ก.ย.": [{ORTH: "ก.ย.", LEMMA: "กันยายน"}],
-    "ต.ค.": [{ORTH: "ต.ค.", LEMMA: "ตุลาคม"}],
-    "พ.ย.": [{ORTH: "พ.ย.", LEMMA: "พฤศจิกายน"}],
-    "ธ.ค.": [{ORTH: "ธ.ค.", LEMMA: "ธันวาคม"}],
+    "ม.ค.": [{ORTH: "ม.ค."}],
+    "ก.พ.": [{ORTH: "ก.พ."}],
+    "มี.ค.": [{ORTH: "มี.ค."}],
+    "เม.ย.": [{ORTH: "เม.ย."}],
+    "พ.ค.": [{ORTH: "พ.ค."}],
+    "มิ.ย.": [{ORTH: "มิ.ย."}],
+    "ก.ค.": [{ORTH: "ก.ค."}],
+    "ส.ค.": [{ORTH: "ส.ค."}],
+    "ก.ย.": [{ORTH: "ก.ย."}],
+    "ต.ค.": [{ORTH: "ต.ค."}],
+    "พ.ย.": [{ORTH: "พ.ย."}],
+    "ธ.ค.": [{ORTH: "ธ.ค."}],
     # เพศ / gender
-    "ช.": [{ORTH: "ช.", LEMMA: "ชาย"}],
-    "ญ.": [{ORTH: "ญ.", LEMMA: "หญิง"}],
-    "ด.ช.": [{ORTH: "ด.ช.", LEMMA: "เด็กชาย"}],
-    "ด.ญ.": [{ORTH: "ด.ญ.", LEMMA: "เด็กหญิง"}],
+    "ช.": [{ORTH: "ช."}],
+    "ญ.": [{ORTH: "ญ."}],
+    "ด.ช.": [{ORTH: "ด.ช."}],
+    "ด.ญ.": [{ORTH: "ด.ญ."}],
     # ที่อยู่ / address
-    "ถ.": [{ORTH: "ถ.", LEMMA: "ถนน"}],
-    "ต.": [{ORTH: "ต.", LEMMA: "ตำบล"}],
-    "อ.": [{ORTH: "อ.", LEMMA: "อำเภอ"}],
-    "จ.": [{ORTH: "จ.", LEMMA: "จังหวัด"}],
+    "ถ.": [{ORTH: "ถ."}],
+    "ต.": [{ORTH: "ต."}],
+    "อ.": [{ORTH: "อ."}],
+    "จ.": [{ORTH: "จ."}],
     # สรรพนาม / pronoun
-    "ข้าฯ": [{ORTH: "ข้าฯ", LEMMA: "ข้าพระพุทธเจ้า"}],
-    "ทูลเกล้าฯ": [{ORTH: "ทูลเกล้าฯ", LEMMA: "ทูลเกล้าทูลกระหม่อม"}],
-    "น้อมเกล้าฯ": [{ORTH: "น้อมเกล้าฯ", LEMMA: "น้อมเกล้าน้อมกระหม่อม"}],
-    "โปรดเกล้าฯ": [{ORTH: "โปรดเกล้าฯ", LEMMA: "โปรดเกล้าโปรดกระหม่อม"}],
+    "ข้าฯ": [{ORTH: "ข้าฯ"}],
+    "ทูลเกล้าฯ": [{ORTH: "ทูลเกล้าฯ"}],
+    "น้อมเกล้าฯ": [{ORTH: "น้อมเกล้าฯ"}],
+    "โปรดเกล้าฯ": [{ORTH: "โปรดเกล้าฯ"}],
     # การเมือง / politic
-    "ขจก.": [{ORTH: "ขจก.", LEMMA: "ขบวนการโจรก่อการร้าย"}],
-    "ขบด.": [{ORTH: "ขบด.", LEMMA: "ขบวนการแบ่งแยกดินแดน"}],
-    "นปช.": [{ORTH: "นปช.", LEMMA: "แนวร่วมประชาธิปไตยขับไล่เผด็จการ"}],
-    "ปชป.": [{ORTH: "ปชป.", LEMMA: "พรรคประชาธิปัตย์"}],
-    "ผกค.": [{ORTH: "ผกค.", LEMMA: "ผู้ก่อการร้ายคอมมิวนิสต์"}],
-    "พท.": [{ORTH: "พท.", LEMMA: "พรรคเพื่อไทย"}],
-    "พ.ร.ก.": [{ORTH: "พ.ร.ก.", LEMMA: "พระราชกำหนด"}],
-    "พ.ร.ฎ.": [{ORTH: "พ.ร.ฎ.", LEMMA: "พระราชกฤษฎีกา"}],
-    "พ.ร.บ.": [{ORTH: "พ.ร.บ.", LEMMA: "พระราชบัญญัติ"}],
-    "รธน.": [{ORTH: "รธน.", LEMMA: "รัฐธรรมนูญ"}],
-    "รบ.": [{ORTH: "รบ.", LEMMA: "รัฐบาล"}],
-    "รสช.": [{ORTH: "รสช.", LEMMA: "คณะรักษาความสงบเรียบร้อยแห่งชาติ"}],
-    "ส.ก.": [{ORTH: "ส.ก.", LEMMA: "สมาชิกสภากรุงเทพมหานคร"}],
-    "สจ.": [{ORTH: "สจ.", LEMMA: "สมาชิกสภาจังหวัด"}],
-    "สว.": [{ORTH: "สว.", LEMMA: "สมาชิกวุฒิสภา"}],
-    "ส.ส.": [{ORTH: "ส.ส.", LEMMA: "สมาชิกสภาผู้แทนราษฎร"}],
+    "ขจก.": [{ORTH: "ขจก."}],
+    "ขบด.": [{ORTH: "ขบด."}],
+    "นปช.": [{ORTH: "นปช."}],
+    "ปชป.": [{ORTH: "ปชป."}],
+    "ผกค.": [{ORTH: "ผกค."}],
+    "พท.": [{ORTH: "พท."}],
+    "พ.ร.ก.": [{ORTH: "พ.ร.ก."}],
+    "พ.ร.ฎ.": [{ORTH: "พ.ร.ฎ."}],
+    "พ.ร.บ.": [{ORTH: "พ.ร.บ."}],
+    "รธน.": [{ORTH: "รธน."}],
+    "รบ.": [{ORTH: "รบ."}],
+    "รสช.": [{ORTH: "รสช."}],
+    "ส.ก.": [{ORTH: "ส.ก."}],
+    "สจ.": [{ORTH: "สจ."}],
+    "สว.": [{ORTH: "สว."}],
+    "ส.ส.": [{ORTH: "ส.ส."}],
     # ทั่วไป / general
-    "ก.ข.ค.": [{ORTH: "ก.ข.ค.", LEMMA: "ก้างขวางคอ"}],
-    "กทม.": [{ORTH: "กทม.", LEMMA: "กรุงเทพมหานคร"}],
-    "กรุงเทพฯ": [{ORTH: "กรุงเทพฯ", LEMMA: "กรุงเทพมหานคร"}],
-    "ขรก.": [{ORTH: "ขรก.", LEMMA: "ข้าราชการ"}],
-    "ขส": [{ORTH: "ขส.", LEMMA: "ขนส่ง"}],
-    "ค.ร.น.": [{ORTH: "ค.ร.น.", LEMMA: "คูณร่วมน้อย"}],
-    "ค.ร.ม.": [{ORTH: "ค.ร.ม.", LEMMA: "คูณร่วมมาก"}],
-    "ง.ด.": [{ORTH: "ง.ด.", LEMMA: "เงินเดือน"}],
-    "งป.": [{ORTH: "งป.", LEMMA: "งบประมาณ"}],
-    "จก.": [{ORTH: "จก.", LEMMA: "จำกัด"}],
-    "จขกท.": [{ORTH: "จขกท.", LEMMA: "เจ้าของกระทู้"}],
-    "จนท.": [{ORTH: "จนท.", LEMMA: "เจ้าหน้าที่"}],
-    "จ.ป.ร.": [
-        {
-            ORTH: "จ.ป.ร.",
-            LEMMA: "มหาจุฬาลงกรณ ปรมราชาธิราช (พระปรมาภิไธยในพระบาทสมเด็จพระจุลจอมเกล้าเจ้าอยู่หัว)",
-        }
-    ],
-    "จ.ม.": [{ORTH: "จ.ม.", LEMMA: "จดหมาย"}],
-    "จย.": [{ORTH: "จย.", LEMMA: "จักรยาน"}],
-    "จยย.": [{ORTH: "จยย.", LEMMA: "จักรยานยนต์"}],
-    "ตจว.": [{ORTH: "ตจว.", LEMMA: "ต่างจังหวัด"}],
-    "โทร.": [{ORTH: "โทร.", LEMMA: "โทรศัพท์"}],
-    "ธ.": [{ORTH: "ธ.", LEMMA: "ธนาคาร"}],
-    "น.ร.": [{ORTH: "น.ร.", LEMMA: "นักเรียน"}],
-    "น.ศ.": [{ORTH: "น.ศ.", LEMMA: "นักศึกษา"}],
-    "น.ส.": [{ORTH: "น.ส.", LEMMA: "นางสาว"}],
-    "น.ส.๓": [{ORTH: "น.ส.๓", LEMMA: "หนังสือรับรองการทำประโยชน์ในที่ดิน"}],
-    "น.ส.๓ ก.": [
-        {ORTH: "น.ส.๓ ก", LEMMA: "หนังสือแสดงกรรมสิทธิ์ในที่ดิน (มีระวางกำหนด)"}
-    ],
-    "นสพ.": [{ORTH: "นสพ.", LEMMA: "หนังสือพิมพ์"}],
-    "บ.ก.": [{ORTH: "บ.ก.", LEMMA: "บรรณาธิการ"}],
-    "บจก.": [{ORTH: "บจก.", LEMMA: "บริษัทจำกัด"}],
-    "บงล.": [{ORTH: "บงล.", LEMMA: "บริษัทเงินทุนและหลักทรัพย์จำกัด"}],
-    "บบส.": [{ORTH: "บบส.", LEMMA: "บรรษัทบริหารสินทรัพย์สถาบันการเงิน"}],
-    "บมจ.": [{ORTH: "บมจ.", LEMMA: "บริษัทมหาชนจำกัด"}],
-    "บลจ.": [{ORTH: "บลจ.", LEMMA: "บริษัทหลักทรัพย์จัดการกองทุนรวมจำกัด"}],
-    "บ/ช": [{ORTH: "บ/ช", LEMMA: "บัญชี"}],
-    "บร.": [{ORTH: "บร.", LEMMA: "บรรณารักษ์"}],
-    "ปชช.": [{ORTH: "ปชช.", LEMMA: "ประชาชน"}],
-    "ปณ.": [{ORTH: "ปณ.", LEMMA: "ที่ทำการไปรษณีย์"}],
-    "ปณก.": [{ORTH: "ปณก.", LEMMA: "ที่ทำการไปรษณีย์กลาง"}],
-    "ปณส.": [{ORTH: "ปณส.", LEMMA: "ที่ทำการไปรษณีย์สาขา"}],
-    "ปธ.": [{ORTH: "ปธ.", LEMMA: "ประธาน"}],
-    "ปธน.": [{ORTH: "ปธน.", LEMMA: "ประธานาธิบดี"}],
-    "ปอ.": [{ORTH: "ปอ.", LEMMA: "รถยนต์โดยสารประจำทางปรับอากาศ"}],
-    "ปอ.พ.": [{ORTH: "ปอ.พ.", LEMMA: "รถยนต์โดยสารประจำทางปรับอากาศพิเศษ"}],
-    "พ.ก.ง.": [{ORTH: "พ.ก.ง.", LEMMA: "พัสดุเก็บเงินปลายทาง"}],
-    "พ.ก.ส.": [{ORTH: "พ.ก.ส.", LEMMA: "พนักงานเก็บค่าโดยสาร"}],
-    "พขร.": [{ORTH: "พขร.", LEMMA: "พนักงานขับรถ"}],
-    "ภ.ง.ด.": [{ORTH: "ภ.ง.ด.", LEMMA: "ภาษีเงินได้"}],
-    "ภ.ง.ด.๙": [{ORTH: "ภ.ง.ด.๙", LEMMA: "แบบแสดงรายการเสียภาษีเงินได้ของกรมสรรพากร"}],
-    "ภ.ป.ร.": [
-        {
-            ORTH: "ภ.ป.ร.",
-            LEMMA: "ภูมิพลอดุยเดช ปรมราชาธิราช (พระปรมาภิไธยในพระบาทสมเด็จพระปรมินทรมหาภูมิพลอดุลยเดช)",
-        }
-    ],
-    "ภ.พ.": [{ORTH: "ภ.พ.", LEMMA: "ภาษีมูลค่าเพิ่ม"}],
-    "ร.": [{ORTH: "ร.", LEMMA: "รัชกาล"}],
-    "ร.ง.": [{ORTH: "ร.ง.", LEMMA: "โรงงาน"}],
-    "ร.ด.": [{ORTH: "ร.ด.", LEMMA: "รักษาดินแดน"}],
-    "รปภ.": [{ORTH: "รปภ.", LEMMA: "รักษาความปลอดภัย"}],
-    "รพ.": [{ORTH: "รพ.", LEMMA: "โรงพยาบาล"}],
-    "ร.พ.": [{ORTH: "ร.พ.", LEMMA: "โรงพิมพ์"}],
-    "รร.": [{ORTH: "รร.", LEMMA: "โรงเรียน,โรงแรม"}],
-    "รสก.": [{ORTH: "รสก.", LEMMA: "รัฐวิสาหกิจ"}],
-    "ส.ค.ส.": [{ORTH: "ส.ค.ส.", LEMMA: "ส่งความสุขปีใหม่"}],
-    "สต.": [{ORTH: "สต.", LEMMA: "สตางค์"}],
-    "สน.": [{ORTH: "สน.", LEMMA: "สถานีตำรวจ"}],
-    "สนข.": [{ORTH: "สนข.", LEMMA: "สำนักงานเขต"}],
-    "สนง.": [{ORTH: "สนง.", LEMMA: "สำนักงาน"}],
-    "สนญ.": [{ORTH: "สนญ.", LEMMA: "สำนักงานใหญ่"}],
-    "ส.ป.ช.": [{ORTH: "ส.ป.ช.", LEMMA: "สร้างเสริมประสบการณ์ชีวิต"}],
-    "สภ.": [{ORTH: "สภ.", LEMMA: "สถานีตำรวจภูธร"}],
-    "ส.ล.น.": [{ORTH: "ส.ล.น.", LEMMA: "สร้างเสริมลักษณะนิสัย"}],
-    "สวญ.": [{ORTH: "สวญ.", LEMMA: "สารวัตรใหญ่"}],
-    "สวป.": [{ORTH: "สวป.", LEMMA: "สารวัตรป้องกันปราบปราม"}],
-    "สว.สส.": [{ORTH: "สว.สส.", LEMMA: "สารวัตรสืบสวน"}],
-    "ส.ห.": [{ORTH: "ส.ห.", LEMMA: "สารวัตรทหาร"}],
-    "สอ.": [{ORTH: "สอ.", LEMMA: "สถานีอนามัย"}],
-    "สอท.": [{ORTH: "สอท.", LEMMA: "สถานเอกอัครราชทูต"}],
-    "เสธ.": [{ORTH: "เสธ.", LEMMA: "เสนาธิการ"}],
-    "หจก.": [{ORTH: "หจก.", LEMMA: "ห้างหุ้นส่วนจำกัด"}],
-    "ห.ร.ม.": [{ORTH: "ห.ร.ม.", LEMMA: "ตัวหารร่วมมาก"}],
+    "ก.ข.ค.": [{ORTH: "ก.ข.ค."}],
+    "กทม.": [{ORTH: "กทม."}],
+    "กรุงเทพฯ": [{ORTH: "กรุงเทพฯ"}],
+    "ขรก.": [{ORTH: "ขรก."}],
+    "ขส": [{ORTH: "ขส."}],
+    "ค.ร.น.": [{ORTH: "ค.ร.น."}],
+    "ค.ร.ม.": [{ORTH: "ค.ร.ม."}],
+    "ง.ด.": [{ORTH: "ง.ด."}],
+    "งป.": [{ORTH: "งป."}],
+    "จก.": [{ORTH: "จก."}],
+    "จขกท.": [{ORTH: "จขกท."}],
+    "จนท.": [{ORTH: "จนท."}],
+    "จ.ป.ร.": [{ORTH: "จ.ป.ร."}],
+    "จ.ม.": [{ORTH: "จ.ม."}],
+    "จย.": [{ORTH: "จย."}],
+    "จยย.": [{ORTH: "จยย."}],
+    "ตจว.": [{ORTH: "ตจว."}],
+    "โทร.": [{ORTH: "โทร."}],
+    "ธ.": [{ORTH: "ธ."}],
+    "น.ร.": [{ORTH: "น.ร."}],
+    "น.ศ.": [{ORTH: "น.ศ."}],
+    "น.ส.": [{ORTH: "น.ส."}],
+    "น.ส.๓": [{ORTH: "น.ส.๓"}],
+    "น.ส.๓ ก.": [{ORTH: "น.ส.๓ ก"}],
+    "นสพ.": [{ORTH: "นสพ."}],
+    "บ.ก.": [{ORTH: "บ.ก."}],
+    "บจก.": [{ORTH: "บจก."}],
+    "บงล.": [{ORTH: "บงล."}],
+    "บบส.": [{ORTH: "บบส."}],
+    "บมจ.": [{ORTH: "บมจ."}],
+    "บลจ.": [{ORTH: "บลจ."}],
+    "บ/ช": [{ORTH: "บ/ช"}],
+    "บร.": [{ORTH: "บร."}],
+    "ปชช.": [{ORTH: "ปชช."}],
+    "ปณ.": [{ORTH: "ปณ."}],
+    "ปณก.": [{ORTH: "ปณก."}],
+    "ปณส.": [{ORTH: "ปณส."}],
+    "ปธ.": [{ORTH: "ปธ."}],
+    "ปธน.": [{ORTH: "ปธน."}],
+    "ปอ.": [{ORTH: "ปอ."}],
+    "ปอ.พ.": [{ORTH: "ปอ.พ."}],
+    "พ.ก.ง.": [{ORTH: "พ.ก.ง."}],
+    "พ.ก.ส.": [{ORTH: "พ.ก.ส."}],
+    "พขร.": [{ORTH: "พขร."}],
+    "ภ.ง.ด.": [{ORTH: "ภ.ง.ด."}],
+    "ภ.ง.ด.๙": [{ORTH: "ภ.ง.ด.๙"}],
+    "ภ.ป.ร.": [{ORTH: "ภ.ป.ร."}],
+    "ภ.พ.": [{ORTH: "ภ.พ."}],
+    "ร.": [{ORTH: "ร."}],
+    "ร.ง.": [{ORTH: "ร.ง."}],
+    "ร.ด.": [{ORTH: "ร.ด."}],
+    "รปภ.": [{ORTH: "รปภ."}],
+    "รพ.": [{ORTH: "รพ."}],
+    "ร.พ.": [{ORTH: "ร.พ."}],
+    "รร.": [{ORTH: "รร."}],
+    "รสก.": [{ORTH: "รสก."}],
+    "ส.ค.ส.": [{ORTH: "ส.ค.ส."}],
+    "สต.": [{ORTH: "สต."}],
+    "สน.": [{ORTH: "สน."}],
+    "สนข.": [{ORTH: "สนข."}],
+    "สนง.": [{ORTH: "สนง."}],
+    "สนญ.": [{ORTH: "สนญ."}],
+    "ส.ป.ช.": [{ORTH: "ส.ป.ช."}],
+    "สภ.": [{ORTH: "สภ."}],
+    "ส.ล.น.": [{ORTH: "ส.ล.น."}],
+    "สวญ.": [{ORTH: "สวญ."}],
+    "สวป.": [{ORTH: "สวป."}],
+    "สว.สส.": [{ORTH: "สว.สส."}],
+    "ส.ห.": [{ORTH: "ส.ห."}],
+    "สอ.": [{ORTH: "สอ."}],
+    "สอท.": [{ORTH: "สอท."}],
+    "เสธ.": [{ORTH: "เสธ."}],
+    "หจก.": [{ORTH: "หจก."}],
+    "ห.ร.ม.": [{ORTH: "ห.ร.ม."}],
 }
 
 
diff --git a/spacy/lang/tl/tokenizer_exceptions.py b/spacy/lang/tl/tokenizer_exceptions.py
index f81d35f20..51ad12d9f 100644
--- a/spacy/lang/tl/tokenizer_exceptions.py
+++ b/spacy/lang/tl/tokenizer_exceptions.py
@@ -1,18 +1,18 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
 _exc = {
-    "tayo'y": [{ORTH: "tayo", LEMMA: "tayo"}, {ORTH: "'y", LEMMA: "ay"}],
-    "isa'y": [{ORTH: "isa", LEMMA: "isa"}, {ORTH: "'y", LEMMA: "ay"}],
-    "baya'y": [{ORTH: "baya", LEMMA: "bayan"}, {ORTH: "'y", LEMMA: "ay"}],
-    "sa'yo": [{ORTH: "sa", LEMMA: "sa"}, {ORTH: "'yo", LEMMA: "iyo"}],
-    "ano'ng": [{ORTH: "ano", LEMMA: "ano"}, {ORTH: "'ng", LEMMA: "ang"}],
-    "siya'y": [{ORTH: "siya", LEMMA: "siya"}, {ORTH: "'y", LEMMA: "ay"}],
-    "nawa'y": [{ORTH: "nawa", LEMMA: "nawa"}, {ORTH: "'y", LEMMA: "ay"}],
-    "papa'no": [{ORTH: "papa'no", LEMMA: "papaano"}],
-    "'di": [{ORTH: "'di", LEMMA: "hindi"}],
+    "tayo'y": [{ORTH: "tayo"}, {ORTH: "'y", NORM: "ay"}],
+    "isa'y": [{ORTH: "isa"}, {ORTH: "'y", NORM: "ay"}],
+    "baya'y": [{ORTH: "baya"}, {ORTH: "'y", NORM: "ay"}],
+    "sa'yo": [{ORTH: "sa"}, {ORTH: "'yo", NORM: "iyo"}],
+    "ano'ng": [{ORTH: "ano"}, {ORTH: "'ng", NORM: "ang"}],
+    "siya'y": [{ORTH: "siya"}, {ORTH: "'y", NORM: "ay"}],
+    "nawa'y": [{ORTH: "nawa"}, {ORTH: "'y", NORM: "ay"}],
+    "papa'no": [{ORTH: "papa'no", NORM: "papaano"}],
+    "'di": [{ORTH: "'di", NORM: "hindi"}],
 }
 
 
diff --git a/spacy/lang/tokenizer_exceptions.py b/spacy/lang/tokenizer_exceptions.py
index 45391332e..2532ae104 100644
--- a/spacy/lang/tokenizer_exceptions.py
+++ b/spacy/lang/tokenizer_exceptions.py
@@ -1,7 +1,7 @@
 import re
 
 from .char_classes import ALPHA_LOWER
-from ..symbols import ORTH, POS, TAG, LEMMA, SPACE
+from ..symbols import ORTH, NORM
 
 
 # URL validation regex courtesy of: https://mathiasbynens.be/demo/url-regex
@@ -62,13 +62,13 @@ BASE_EXCEPTIONS = {}
 
 
 for exc_data in [
-    {ORTH: " ", POS: SPACE, TAG: "_SP"},
-    {ORTH: "\t", POS: SPACE, TAG: "_SP"},
-    {ORTH: "\\t", POS: SPACE, TAG: "_SP"},
-    {ORTH: "\n", POS: SPACE, TAG: "_SP"},
-    {ORTH: "\\n", POS: SPACE, TAG: "_SP"},
+    {ORTH: " "},
+    {ORTH: "\t"},
+    {ORTH: "\\t"},
+    {ORTH: "\n"},
+    {ORTH: "\\n"},
     {ORTH: "\u2014"},
-    {ORTH: "\u00a0", POS: SPACE, LEMMA: "  ", TAG: "_SP"},
+    {ORTH: "\u00a0", NORM: "  "},
 ]:
     BASE_EXCEPTIONS[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/lang/tt/tokenizer_exceptions.py b/spacy/lang/tt/tokenizer_exceptions.py
index 4ee6b6cd2..3b8cc86b5 100644
--- a/spacy/lang/tt/tokenizer_exceptions.py
+++ b/spacy/lang/tt/tokenizer_exceptions.py
@@ -1,5 +1,5 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
@@ -7,35 +7,35 @@ _exc = {}
 
 _abbrev_exc = [
     # Weekdays abbreviations
-    {ORTH: "дш", LEMMA: "дүшәмбе"},
-    {ORTH: "сш", LEMMA: "сишәмбе"},
-    {ORTH: "чш", LEMMA: "чәршәмбе"},
-    {ORTH: "пш", LEMMA: "пәнҗешәмбе"},
-    {ORTH: "җм", LEMMA: "җомга"},
-    {ORTH: "шб", LEMMA: "шимбә"},
-    {ORTH: "яш", LEMMA: "якшәмбе"},
+    {ORTH: "дш", NORM: "дүшәмбе"},
+    {ORTH: "сш", NORM: "сишәмбе"},
+    {ORTH: "чш", NORM: "чәршәмбе"},
+    {ORTH: "пш", NORM: "пәнҗешәмбе"},
+    {ORTH: "җм", NORM: "җомга"},
+    {ORTH: "шб", NORM: "шимбә"},
+    {ORTH: "яш", NORM: "якшәмбе"},
     # Months abbreviations
-    {ORTH: "гый", LEMMA: "гыйнвар"},
-    {ORTH: "фев", LEMMA: "февраль"},
-    {ORTH: "мар", LEMMA: "март"},
-    {ORTH: "мар", LEMMA: "март"},
-    {ORTH: "апр", LEMMA: "апрель"},
-    {ORTH: "июн", LEMMA: "июнь"},
-    {ORTH: "июл", LEMMA: "июль"},
-    {ORTH: "авг", LEMMA: "август"},
-    {ORTH: "сен", LEMMA: "сентябрь"},
-    {ORTH: "окт", LEMMA: "октябрь"},
-    {ORTH: "ноя", LEMMA: "ноябрь"},
-    {ORTH: "дек", LEMMA: "декабрь"},
+    {ORTH: "гый", NORM: "гыйнвар"},
+    {ORTH: "фев", NORM: "февраль"},
+    {ORTH: "мар", NORM: "март"},
+    {ORTH: "мар", NORM: "март"},
+    {ORTH: "апр", NORM: "апрель"},
+    {ORTH: "июн", NORM: "июнь"},
+    {ORTH: "июл", NORM: "июль"},
+    {ORTH: "авг", NORM: "август"},
+    {ORTH: "сен", NORM: "сентябрь"},
+    {ORTH: "окт", NORM: "октябрь"},
+    {ORTH: "ноя", NORM: "ноябрь"},
+    {ORTH: "дек", NORM: "декабрь"},
     # Number abbreviations
-    {ORTH: "млрд", LEMMA: "миллиард"},
-    {ORTH: "млн", LEMMA: "миллион"},
+    {ORTH: "млрд", NORM: "миллиард"},
+    {ORTH: "млн", NORM: "миллион"},
 ]
 
 for abbr in _abbrev_exc:
     for orth in (abbr[ORTH], abbr[ORTH].capitalize(), abbr[ORTH].upper()):
-        _exc[orth] = [{ORTH: orth, LEMMA: abbr[LEMMA], NORM: abbr[LEMMA]}]
-        _exc[orth + "."] = [{ORTH: orth + ".", LEMMA: abbr[LEMMA], NORM: abbr[LEMMA]}]
+        _exc[orth] = [{ORTH: orth, NORM: abbr[NORM]}]
+        _exc[orth + "."] = [{ORTH: orth + ".", NORM: abbr[NORM]}]
 
 for exc_data in [  # "etc." abbreviations
     {ORTH: "һ.б.ш.", NORM: "һәм башка шундыйлар"},
@@ -43,7 +43,6 @@ for exc_data in [  # "etc." abbreviations
     {ORTH: "б.э.к.", NORM: "безнең эрага кадәр"},
     {ORTH: "б.э.", NORM: "безнең эра"},
 ]:
-    exc_data[LEMMA] = exc_data[NORM]
     _exc[exc_data[ORTH]] = [exc_data]
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
diff --git a/spacy/lang/uk/tokenizer_exceptions.py b/spacy/lang/uk/tokenizer_exceptions.py
index 8ae82a48c..94016fd52 100644
--- a/spacy/lang/uk/tokenizer_exceptions.py
+++ b/spacy/lang/uk/tokenizer_exceptions.py
@@ -1,24 +1,24 @@
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, LEMMA, POS, NORM, NOUN
+from ...symbols import ORTH, NORM
 from ...util import update_exc
 
 
 _exc = {}
 
 for exc_data in [
-    {ORTH: "вул.", LEMMA: "вулиця", NORM: "вулиця", POS: NOUN},
-    {ORTH: "ім.", LEMMA: "ім'я", NORM: "імені", POS: NOUN},
-    {ORTH: "просп.", LEMMA: "проспект", NORM: "проспект", POS: NOUN},
-    {ORTH: "бул.", LEMMA: "бульвар", NORM: "бульвар", POS: NOUN},
-    {ORTH: "пров.", LEMMA: "провулок", NORM: "провулок", POS: NOUN},
-    {ORTH: "пл.", LEMMA: "площа", NORM: "площа", POS: NOUN},
-    {ORTH: "г.", LEMMA: "гора", NORM: "гора", POS: NOUN},
-    {ORTH: "п.", LEMMA: "пан", NORM: "пан", POS: NOUN},
-    {ORTH: "м.", LEMMA: "місто", NORM: "місто", POS: NOUN},
-    {ORTH: "проф.", LEMMA: "професор", NORM: "професор", POS: NOUN},
-    {ORTH: "акад.", LEMMA: "академік", NORM: "академік", POS: NOUN},
-    {ORTH: "доц.", LEMMA: "доцент", NORM: "доцент", POS: NOUN},
-    {ORTH: "оз.", LEMMA: "озеро", NORM: "озеро", POS: NOUN},
+    {ORTH: "вул.", NORM: "вулиця"},
+    {ORTH: "ім.", NORM: "імені"},
+    {ORTH: "просп.", NORM: "проспект"},
+    {ORTH: "бул.", NORM: "бульвар"},
+    {ORTH: "пров.", NORM: "провулок"},
+    {ORTH: "пл.", NORM: "площа"},
+    {ORTH: "г.", NORM: "гора"},
+    {ORTH: "п.", NORM: "пан"},
+    {ORTH: "м.", NORM: "місто"},
+    {ORTH: "проф.", NORM: "професор"},
+    {ORTH: "акад.", NORM: "академік"},
+    {ORTH: "доц.", NORM: "доцент"},
+    {ORTH: "оз.", NORM: "озеро"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 
diff --git a/spacy/tests/lang/ar/test_exceptions.py b/spacy/tests/lang/ar/test_exceptions.py
index 125220caf..0129c3a19 100644
--- a/spacy/tests/lang/ar/test_exceptions.py
+++ b/spacy/tests/lang/ar/test_exceptions.py
@@ -12,7 +12,6 @@ def test_ar_tokenizer_handles_exc_in_text(ar_tokenizer):
     tokens = ar_tokenizer(text)
     assert len(tokens) == 7
     assert tokens[6].text == "ق.م"
-    assert tokens[6].lemma_ == "قبل الميلاد"
 
 
 def test_ar_tokenizer_handles_exc_in_text_2(ar_tokenizer):
diff --git a/spacy/tests/lang/ca/test_exception.py b/spacy/tests/lang/ca/test_exception.py
index 71098f094..cfb574b63 100644
--- a/spacy/tests/lang/ca/test_exception.py
+++ b/spacy/tests/lang/ca/test_exception.py
@@ -8,7 +8,6 @@ import pytest
 def test_ca_tokenizer_handles_abbr(ca_tokenizer, text, lemma):
     tokens = ca_tokenizer(text)
     assert len(tokens) == 1
-    assert tokens[0].lemma_ == lemma
 
 
 def test_ca_tokenizer_handles_exc_in_text(ca_tokenizer):
@@ -16,4 +15,3 @@ def test_ca_tokenizer_handles_exc_in_text(ca_tokenizer):
     tokens = ca_tokenizer(text)
     assert len(tokens) == 15
     assert tokens[7].text == "aprox."
-    assert tokens[7].lemma_ == "aproximadament"
diff --git a/spacy/tests/lang/de/test_exceptions.py b/spacy/tests/lang/de/test_exceptions.py
index a1bbaf58b..d51c33992 100644
--- a/spacy/tests/lang/de/test_exceptions.py
+++ b/spacy/tests/lang/de/test_exceptions.py
@@ -18,4 +18,3 @@ def test_de_tokenizer_handles_exc_in_text(de_tokenizer):
     tokens = de_tokenizer(text)
     assert len(tokens) == 6
     assert tokens[2].text == "z.Zt."
-    assert tokens[2].lemma_ == "zur Zeit"
diff --git a/spacy/tests/lang/en/test_exceptions.py b/spacy/tests/lang/en/test_exceptions.py
index f72dfbf25..1b56a3b0f 100644
--- a/spacy/tests/lang/en/test_exceptions.py
+++ b/spacy/tests/lang/en/test_exceptions.py
@@ -49,7 +49,6 @@ def test_en_tokenizer_handles_ll_contraction(en_tokenizer, text):
     assert len(tokens) == 2
     assert tokens[0].text == text.split("'")[0]
     assert tokens[1].text == "'ll"
-    assert tokens[1].lemma_ == "will"
 
 
 @pytest.mark.parametrize(
@@ -104,7 +103,6 @@ def test_en_tokenizer_handles_exc_in_text(en_tokenizer):
 def test_en_tokenizer_handles_times(en_tokenizer, text):
     tokens = en_tokenizer(text)
     assert len(tokens) == 2
-    assert tokens[1].lemma_ in ["a.m.", "p.m."]
 
 
 @pytest.mark.parametrize(
diff --git a/spacy/tests/lang/es/test_exception.py b/spacy/tests/lang/es/test_exception.py
index 90d897a4c..07df5d69e 100644
--- a/spacy/tests/lang/es/test_exception.py
+++ b/spacy/tests/lang/es/test_exception.py
@@ -13,7 +13,6 @@ import pytest
 def test_es_tokenizer_handles_abbr(es_tokenizer, text, lemma):
     tokens = es_tokenizer(text)
     assert len(tokens) == 1
-    assert tokens[0].lemma_ == lemma
 
 
 def test_es_tokenizer_handles_exc_in_text(es_tokenizer):
@@ -21,4 +20,3 @@ def test_es_tokenizer_handles_exc_in_text(es_tokenizer):
     tokens = es_tokenizer(text)
     assert len(tokens) == 7
     assert tokens[4].text == "aprox."
-    assert tokens[4].lemma_ == "aproximadamente"
diff --git a/spacy/tests/lang/fr/test_exceptions.py b/spacy/tests/lang/fr/test_exceptions.py
index 4b7ccad65..77e72a76b 100644
--- a/spacy/tests/lang/fr/test_exceptions.py
+++ b/spacy/tests/lang/fr/test_exceptions.py
@@ -37,19 +37,11 @@ def test_fr_tokenizer_infix_exceptions(fr_tokenizer, text):
 
 
 @pytest.mark.parametrize(
-    "text,lemma",
-    [
-        ("janv.", "janvier"),
-        ("juill.", "juillet"),
-        ("Dr.", "docteur"),
-        ("av.", "avant"),
-        ("sept.", "septembre"),
-    ],
+    "text", ["janv.", "juill.", "Dr.", "av.", "sept."],
 )
-def test_fr_tokenizer_handles_abbr(fr_tokenizer, text, lemma):
+def test_fr_tokenizer_handles_abbr(fr_tokenizer, text):
     tokens = fr_tokenizer(text)
     assert len(tokens) == 1
-    assert tokens[0].lemma_ == lemma
 
 
 def test_fr_tokenizer_handles_exc_in_text(fr_tokenizer):
@@ -57,7 +49,6 @@ def test_fr_tokenizer_handles_exc_in_text(fr_tokenizer):
     tokens = fr_tokenizer(text)
     assert len(tokens) == 10
     assert tokens[6].text == "janv."
-    assert tokens[6].lemma_ == "janvier"
     assert tokens[8].text == "prud’hommes"
 
 
@@ -74,11 +65,8 @@ def test_fr_tokenizer_handles_title(fr_tokenizer):
     tokens = fr_tokenizer(text)
     assert len(tokens) == 6
     assert tokens[0].text == "N'"
-    assert tokens[0].lemma_ == "ne"
     assert tokens[1].text == "est"
-    assert tokens[1].lemma_ == "être"
     assert tokens[2].text == "-ce"
-    assert tokens[2].lemma_ == "ce"
 
 
 def test_fr_tokenizer_handles_title_2(fr_tokenizer):
@@ -86,9 +74,7 @@ def test_fr_tokenizer_handles_title_2(fr_tokenizer):
     tokens = fr_tokenizer(text)
     assert len(tokens) == 5
     assert tokens[0].text == "Est"
-    assert tokens[0].lemma_ == "être"
     assert tokens[1].text == "-ce"
-    assert tokens[1].lemma_ == "ce"
 
 
 def test_fr_tokenizer_handles_title_3(fr_tokenizer):
@@ -96,4 +82,3 @@ def test_fr_tokenizer_handles_title_3(fr_tokenizer):
     tokens = fr_tokenizer(text)
     assert len(tokens) == 7
     assert tokens[0].text == "Qu'"
-    assert tokens[0].lemma_ == "que"
diff --git a/spacy/tests/lang/lb/test_exceptions.py b/spacy/tests/lang/lb/test_exceptions.py
index d941a854b..fc4b4fa7b 100644
--- a/spacy/tests/lang/lb/test_exceptions.py
+++ b/spacy/tests/lang/lb/test_exceptions.py
@@ -18,4 +18,3 @@ def test_lb_tokenizer_handles_exc_in_text(lb_tokenizer):
     tokens = lb_tokenizer(text)
     assert len(tokens) == 9
     assert tokens[1].text == "'t"
-    assert tokens[1].lemma_ == "et"
diff --git a/spacy/tests/regression/test_issue1501-2000.py b/spacy/tests/regression/test_issue1501-2000.py
index 9d2ef999b..b5d586ec6 100644
--- a/spacy/tests/regression/test_issue1501-2000.py
+++ b/spacy/tests/regression/test_issue1501-2000.py
@@ -157,8 +157,6 @@ def test_issue1758(en_tokenizer):
     """Test that "would've" is handled by the English tokenizer exceptions."""
     tokens = en_tokenizer("would've")
     assert len(tokens) == 2
-    assert tokens[0].tag_ == "MD"
-    assert tokens[1].lemma_ == "have"
 
 
 def test_issue1773(en_tokenizer):
diff --git a/spacy/tests/regression/test_issue2501-3000.py b/spacy/tests/regression/test_issue2501-3000.py
index 7917157aa..ac0867189 100644
--- a/spacy/tests/regression/test_issue2501-3000.py
+++ b/spacy/tests/regression/test_issue2501-3000.py
@@ -166,7 +166,6 @@ def test_issue2822(it_tokenizer):
     assert doc[0].text == "Vuoi"
     assert doc[1].text == "un"
     assert doc[2].text == "po'"
-    assert doc[2].lemma_ == "poco"
     assert doc[3].text == "di"
     assert doc[4].text == "zucchero"
     assert doc[5].text == "?"