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

Merge pull request #876 from PySUST/master 

[Bangla] Update "tokenizer_exceptions.py"
This commit is contained in:
Ines Montani 2017-03-10 14:46:00 +01:00 committed by GitHub
parent 10e29189ac 1c40890321
commit a16aff17aa
1 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/bn/tokenizer_exceptions.py
View File

@ -27,10 +27,21 @@ ABBREVIATIONS = {
"সে.": [ "সে.": [
{ORTH: "সে.", LEMMA: "সেলসিয়াস"}, {ORTH: "সে.", LEMMA: "সেলসিয়াস"},
], ],
"কি.মি": [ "কি.মি.": [
{ORTH: "কি.মি", LEMMA: "কিলোমিটার"},
{ORTH: "কি.মি.", LEMMA: "কিলোমিটার"}, {ORTH: "কি.মি.", LEMMA: "কিলোমিটার"},
], ],
"কি.মি": [
{ORTH: "কি.মি", LEMMA: "কিলোমিটার"},
],
"সে.মি.": [
{ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
],
"সে.মি": [
{ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
],
"মি.লি.": [
{ORTH: "মি.লি.", LEMMA: "মিলিলিটার"},
]
} }
TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS) TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS)