explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

update tokenizertokenizer

Browse Source
This commit is contained in:
shuvanon 2017-03-08 17:29:39 +06:00
parent 45bc78461c
commit 85438aee1b
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/bn/tokenizer_exceptions.py
View File

@ -35,6 +35,9 @@ ABBREVIATIONS = {
{ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"}, {ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
{ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"}, {ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
], ],
"মি.লি.": [
{ORTH: "মি.লি.", LEMMA: "মিলিলিটার"},
]
} }
TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS) TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS)