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

Add numbers and definitions (#10665)

Browse Source
This commit is contained in:
Duy Ngo 2022-04-18 12:58:32 +02:00 committed by GitHub
parent d622883a42
commit 229ecaf0ea
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 23 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
spacy/lang/vi/lex_attrs.py
View File

@ -2,22 +2,29 @@ from ...attrs import LIKE_NUM
_num_words = [ _num_words = [
"không", "không", # Zero
"một", "một", # One
"hai", "mốt", # Also one, irreplacable in niché cases for unit digit such as "51"="năm mươi mốt"
"ba", "hai", # Two
"bốn", "ba", # Three
"năm", "bốn", # Four
"sáu", "tư", # Also four, used in certain cases for unit digit such as "54"="năm mươi tư"
"bảy", "năm", # Five
"bẩy", "lăm", # Also five, irreplacable in niché cases for unit digit such as "55"="năm mươi lăm"
"tám", "sáu", # Six
"chín", "bảy", # Seven
"mười", "bẩy", # Also seven, old fashioned
"chục", "tám", # Eight
"trăm", "chín", # Nine
"nghìn", "mười", # Ten
"tỷ", "chục", # Also ten, used for counting in tens such as "20 eggs"="hai chục trứng"
"trăm", # Hundred
"nghìn", # Thousand
"ngàn", # Also thousand, used in the south
"vạn", # Ten thousand
"triệu", # Million
"tỷ", # Billion
"tỉ" # Also billion, used in combinatorics such as "tỉ_phú"="billionaire"
] ]