explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-27 02:16:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add missing tokenizer exceptions (resolves #1281)

Browse Source
This commit is contained in:
ines 2017-08-21 16:11:36 +02:00
parent c5c3f4c7d9
commit edc596d9a7
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/en/tokenizer_exceptions.py
View File

@ -276,7 +276,10 @@ for verb_data in [
{ORTH: "are", LEMMA: "be", TAG: "VBP", "number": 2}, {ORTH: "are", LEMMA: "be", TAG: "VBP", "number": 2},
{ORTH: "is", LEMMA: "be", TAG: "VBZ"}, {ORTH: "is", LEMMA: "be", TAG: "VBZ"},
{ORTH: "was", LEMMA: "be"}, {ORTH: "was", LEMMA: "be"},
{ORTH: "were", LEMMA: "be"} {ORTH: "were", LEMMA: "be"},
{ORTH: "have"},
{ORTH: "has", LEMMA: "have"},
{ORTH: "dare"}
]: ]:
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()