From cc5aeaed29c067f60d11e07496704406a1577a35 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Thu, 6 May 2021 10:43:03 +0200
Subject: [PATCH] Add Chinese PTB tags to glossary (#7993)

---
 spacy/glossary.py | 38 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/spacy/glossary.py b/spacy/glossary.py
index c4a6a5c45..0dc075ca7 100644
--- a/spacy/glossary.py
+++ b/spacy/glossary.py
@@ -58,7 +58,7 @@ GLOSSARY = {
     "FW": "foreign word",
     "HYPH": "punctuation mark, hyphen",
     "IN": "conjunction, subordinating or preposition",
-    "JJ": "adjective",
+    "JJ": "adjective (English), other noun-modifier (Chinese)",
     "JJR": "adjective, comparative",
     "JJS": "adjective, superlative",
     "LS": "list item marker",
@@ -88,7 +88,7 @@ GLOSSARY = {
     "WP": "wh-pronoun, personal",
     "WP$": "wh-pronoun, possessive",
     "WRB": "wh-adverb",
-    "SP": "space",
+    "SP": "space (English), sentence-final particle (Chinese)",
     "ADD": "email",
     "NFP": "superfluous punctuation",
     "GW": "additional word in multi-word expression",
@@ -152,6 +152,40 @@ GLOSSARY = {
     "VVIZU": 'infinitive with "zu", full',
     "VVPP": "perfect participle, full",
     "XY": "non-word containing non-letter",
+    # POS Tags (Chinese)
+    # OntoNotes / Chinese Penn Treebank
+    # https://repository.upenn.edu/cgi/viewcontent.cgi?article=1039&context=ircs_reports
+    "AD": "adverb",
+    "AS": "aspect marker",
+    "BA": "把 in ba-construction",
+    # "CD": "cardinal number",
+    "CS": "subordinating conjunction",
+    "DEC": "的 in a relative clause",
+    "DEG": "associative 的",
+    "DER": "得 in V-de const. and V-de-R",
+    "DEV": "地 before VP",
+    "ETC": "for words 等, 等等",
+    # "FW": "foreign words"
+    "IJ": "interjection",
+    # "JJ": "other noun-modifier",
+    "LB": "被 in long bei-const",
+    "LC": "localizer",
+    "M": "measure word",
+    "MSP": "other particle",
+    # "NN": "common noun",
+    "NR": "proper noun",
+    "NT": "temporal noun",
+    "OD": "ordinal number",
+    "ON": "onomatopoeia",
+    "P": "preposition excluding 把 and 被",
+    "PN": "pronoun",
+    "PU": "punctuation",
+    "SB": "被 in short bei-const",
+    # "SP": "sentence-final particle",
+    "VA": "predicative adjective",
+    "VC": "是 (copula)",
+    "VE": "有 as the main verb",
+    "VV": "other verb",
     # Noun chunks
     "NP": "noun phrase",
     "PP": "prepositional phrase",