explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1668 from sorenlind/da_morph

Browse Source 
Add more Danish morph rules and clean up existing ones
This commit is contained in:
Matthew Honnibal 2017-12-06 11:08:09 +01:00 committed by GitHub
commit 3f247119d3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 46 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/da/__init__.py
View File

@ -22,7 +22,7 @@ class DanishDefaults(Language.Defaults):
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
BASE_NORMS, NORM_EXCEPTIONS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
# morph_rules = MORPH_RULES
morph_rules = MORPH_RULES
tag_map = TAG_MAP
stop_words = STOP_WORDS

66
spacy/lang/da/morph_rules.py
View File

@ -3,31 +3,55 @@ from __future__ import unicode_literals
from ...symbols import LEMMA, PRON_LEMMA
# Source: Danish Universal Dependencies and http://fjern-uv.dk/pronom.php
# Note: The Danish Universal Dependencies specify Case=Acc for all instances
# of "den"/"det" even when the case is in fact "Nom". In the rules below, Case
# is left unspecified for "den" and "det".
MORPH_RULES = {
"PRON": {
"jeg": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Case": "Nom"},
"mig": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Case": "Acc"},
"du": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two"},
"han": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Masc", "Case": "Nom"},
"ham": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Masc", "Case": "Acc"},
"hun": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Fem", "Case": "Nom"},
"hende": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Fem", "Case": "Acc"},
"den": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Neut"},
"det": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Neut"},
"vi": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Plur", "Case": "Nom"},
"os": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Plur", "Case": "Acc"},
"de": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Plur", "Case": "Nom"},
"dem": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Plur", "Case": "Acc"},
"jeg": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Case": "Nom", "Gender": "Com"}, # Case=Nom|Gender=Com|Number=Sing|Person=1|PronType=Prs
"mig": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Case": "Acc", "Gender": "Com"}, # Case=Acc|Gender=Com|Number=Sing|Person=1|PronType=Prs
"min": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Poss": "Yes", "Gender": "Com"}, # Gender=Com|Number=Sing|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs
"mit": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Poss": "Yes", "Gender": "Neut"}, # Gender=Neut|Number=Sing|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs
"vor": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Poss": "Yes", "Gender": "Com"}, # Gender=Com|Number=Sing|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form
"vort": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Poss": "Yes", "Gender": "Neut"}, # Gender=Neut|Number=Sing|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form
"du": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Sing", "Case": "Nom", "Gender": "Com"}, # Case=Nom|Gender=Com|Number=Sing|Person=2|PronType=Prs
"dig": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Sing", "Case": "Acc", "Gender": "Com"}, # Case=Acc|Gender=Com|Number=Sing|Person=2|PronType=Prs
"din": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Sing", "Poss": "Yes", "Gender": "Com"}, # Gender=Com|Number=Sing|Number[psor]=Sing|Person=2|Poss=Yes|PronType=Prs
"dit": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Sing", "Poss": "Yes", "Gender": "Neut"}, # Gender=Neut|Number=Sing|Number[psor]=Sing|Person=2|Poss=Yes|PronType=Prs
"han": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Case": "Nom", "Gender": "Com"}, # Case=Nom|Gender=Com|Number=Sing|Person=3|PronType=Prs
"hun": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Case": "Nom", "Gender": "Com"}, # Case=Nom|Gender=Com|Number=Sing|Person=3|PronType=Prs
"den": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Com"}, # Case=Acc|Gender=Com|Number=Sing|Person=3|PronType=Prs, See note above.
"det": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Neut"}, # Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs See note above.
"ham": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Case": "Acc", "Gender": "Com"}, # Case=Acc|Gender=Com|Number=Sing|Person=3|PronType=Prs
"hende": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Case": "Acc", "Gender": "Com"}, # Case=Acc|Gender=Com|Number=Sing|Person=3|PronType=Prs
"sin": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Poss": "Yes", "Gender": "Com", "Reflex": "Yes"}, # Gender=Com|Number=Sing|Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes
"sit": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Poss": "Yes", "Gender": "Neut", "Reflex": "Yes"}, # Gender=Neut|Number=Sing|Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes
"min": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Sing", "Poss": "Yes", "Reflex": "Yes"},
"din": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Sing", "Poss": "Yes", "Reflex": "Yes"},
"hans": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Masc", "Poss": "Yes", "Reflex": "Yes"},
"hendes": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Fem", "Poss": "Yes", "Reflex": "Yes"},
"dens": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Neut", "Poss": "Yes", "Reflex": "Yes"},
"dets": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Sing", "Gender": "Neut", "Poss": "Yes", "Reflex": "Yes"},
"vores": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Plur", "Poss": "Yes", "Reflex": "Yes"},
"deres": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Plur", "Poss": "Yes", "Reflex": "Yes"},
"vi": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Plur", "Case": "Nom", "Gender": "Com"}, # Case=Nom|Gender=Com|Number=Plur|Person=1|PronType=Prs
"os": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Plur", "Case": "Acc", "Gender": "Com"}, # Case=Acc|Gender=Com|Number=Plur|Person=1|PronType=Prs
"mine": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Plur", "Poss": "Yes"}, # Number=Plur|Number[psor]=Sing|Person=1|Poss=Yes|PronType=Prs
"vore": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Number": "Plur", "Poss": "Yes"}, # Number=Plur|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form
"I": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Plur", "Case": "Nom", "Gender": "Com"}, # Case=Nom|Gender=Com|Number=Plur|Person=2|PronType=Prs
"jer": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Plur", "Case": "Acc", "Gender": "Com"}, # Case=Acc|Gender=Com|Number=Plur|Person=2|PronType=Prs
"dine": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Number": "Plur", "Poss": "Yes"}, # Number=Plur|Number[psor]=Sing|Person=2|Poss=Yes|PronType=Prs
"de": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Plur", "Case": "Nom"}, # Case=Nom|Number=Plur|Person=3|PronType=Prs
"dem": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Plur", "Case": "Acc"}, # Case=Acc|Number=Plur|Person=3|PronType=Prs
"sine": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Number": "Plur", "Poss": "Yes", "Reflex": "Yes"}, # Number=Plur|Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes
"vores": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "One", "Poss": "Yes"}, # Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs
"De": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Case": "Nom", "Gender": "Com"}, # Case=Nom|Gender=Com|Person=2|Polite=Form|PronType=Prs
"Dem": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Case": "Acc", "Gender": "Com"}, # Case=Acc|Gender=Com|Person=2|Polite=Form|PronType=Prs
"Deres": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Poss": "Yes"}, # Person=2|Polite=Form|Poss=Yes|PronType=Prs
"jeres": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Two", "Poss": "Yes"}, # Number[psor]=Plur|Person=2|Poss=Yes|PronType=Prs
"sig": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Case": "Acc", "Reflex": "Yes"}, # Case=Acc|Person=3|PronType=Prs|Reflex=Yes
"hans": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Poss": "Yes"}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"hendes": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Poss": "Yes"}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"dens": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Poss": "Yes"}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"dets": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Poss": "Yes"}, # Number[psor]=Sing|Person=3|Poss=Yes|PronType=Prs
"deres": {LEMMA: PRON_LEMMA, "PronType": "Prs", "Person": "Three", "Poss": "Yes"}, # Number[psor]=Plur|Person=3|Poss=Yes|PronType=Prs
},
"VERB": {