explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Port over changes from #1281

Browse Source
This commit is contained in:
ines 2017-08-21 23:19:18 +02:00
parent 5e50a65252
commit a68dc891ea
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/lang/en/tokenizer_exceptions.py
View File

@ -232,7 +232,10 @@ for verb_data in [
{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: "were", LEMMA: "be", NORM: "were"},
{ORTH: "have", NORM: "have"},
{ORTH: "has", LEMMA: "have", NORM: "has"},
{ORTH: "dare", NORM: "dare"}]:
verb_data_tc = dict(verb_data)
verb_data_tc[ORTH] = verb_data_tc[ORTH].title()
for data in [verb_data, verb_data_tc]: