explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add missing tags to verbs (resolves #948)

Browse Source
This commit is contained in:
ines 2017-04-03 18:12:52 +02:00
parent 2c36a61ec5
commit 808cd6cf7f
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/en/tokenizer_exceptions.py
View File

@ -213,15 +213,15 @@ for verb_data in [
{ORTH: "does", LEMMA: "do"}, {ORTH: "does", LEMMA: "do"},
{ORTH: "did", LEMMA: "do", TAG: "VBD"}, {ORTH: "did", LEMMA: "do", TAG: "VBD"},
{ORTH: "had", LEMMA: "have", TAG: "VBD"}, {ORTH: "had", LEMMA: "have", TAG: "VBD"},
{ORTH: "may"}, {ORTH: "may", TAG: "MD"},
{ORTH: "might"}, {ORTH: "might", TAG: "MD"},
{ORTH: "must"}, {ORTH: "must", TAG: "MD"},
{ORTH: "need"}, {ORTH: "need"},
{ORTH: "ought"}, {ORTH: "ought"},
{ORTH: "sha", LEMMA: "shall"}, {ORTH: "sha", LEMMA: "shall", TAG: "MD"},
{ORTH: "should"}, {ORTH: "should", TAG: "MD"},
{ORTH: "wo", LEMMA: "will"}, {ORTH: "wo", LEMMA: "will", TAG: "MD"},
{ORTH: "would"} {ORTH: "would", TAG: "MD"}
]: ]:
verb_data_tc = dict(verb_data) verb_data_tc = dict(verb_data)
verb_data_tc[ORTH] = verb_data_tc[ORTH].title() verb_data_tc[ORTH] = verb_data_tc[ORTH].title()