Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add tokenizer exception for "gonna" (fixes #691)

This commit is contained in:
Ines Montani 2016-12-17 11:59:28 +01:00
parent c69b77d8aa
commit d8d50a0334
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/en/language_data.py
View File

@ -1493,6 +1493,16 @@ TOKENIZER_EXCEPTIONS = {
{ORTH: "ma"} {ORTH: "ma"}
], ],
"gonna": [
{ORTH: "gon", LEMMA: "go"},
{ORTH: "na", LEMMA: "to"}
],
"Gonna": [
{ORTH: "Gon", LEMMA: "go"},
{ORTH: "na", LEMMA: "to"}
],
"whats": [ "whats": [
{ORTH: "what"}, {ORTH: "what"},
{ORTH: "s"} {ORTH: "s"}