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 missing Urdu tags

Browse Source
This commit is contained in:
Muhammad Irfan 2020-04-05 20:55:38 +05:00
parent beef184e53
commit 406d5748b3
1 changed files with 77 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

126
spacy/lang/ur/tag_map.py
View File

@ -1,66 +1,94 @@
# coding: utf8
from __future__ import unicode_literals
from ...symbols import NOUN, PROPN, PART, INTJ, SPACE, PRON, AUX, SCONJ
from ...symbols import POS, PUNCT, SYM, ADJ, CCONJ, NUM, DET, ADV, ADP, X, VERB
from ...symbols import NOUN, PROPN, PART, INTJ, SPACE, PRON
TAG_MAP = {
".": {POS: PUNCT, "PunctType": "peri"},
",": {POS: PUNCT, "PunctType": "comm"},
"-LRB-": {POS: PUNCT, "PunctType": "brck", "PunctSide": "ini"},
"-RRB-": {POS: PUNCT, "PunctType": "brck", "PunctSide": "fin"},
"``": {POS: PUNCT, "PunctType": "quot", "PunctSide": "ini"},
'""': {POS: PUNCT, "PunctType": "quot", "PunctSide": "fin"},
"''": {POS: PUNCT, "PunctType": "quot", "PunctSide": "fin"},
"JJ-Ez": {POS: ADJ},
"INJC": {POS: X},
"QFC": {POS: DET},
"UNK": {POS: X},
"NSTC": {POS: ADV},
"NST": {POS: ADV},
"VMC": {POS: VERB},
"PRPC": {POS: PRON},
"RBC": {POS: ADV},
"PSPC": {POS: ADP},
"INJ": {POS: X},
"JJZ": {POS: ADJ},
"CCC": {POS: SCONJ},
"NN-Ez": {POS: NOUN},
"ECH": {POS: NOUN},
"WQ": {POS: DET},
"RDP": {POS: ADJ},
"JJC": {POS: ADJ},
"NEG": {POS: PART},
"NNZ": {POS: NOUN},
"QO": {POS: ADJ},
"INTFC": {POS: ADV},
"INTF": {POS: ADV},
"NFC": {POS: ADP},
"QCC": {POS: NUM},
"QC": {POS: NUM},
"QF": {POS: DET},
"VAUX": {POS: AUX},
"VM": {POS: VERB},
"DEM": {POS: DET},
"NNPC": {POS: PROPN},
"NNC": {POS: NOUN},
"PSP": {POS: ADP},
".": {POS: PUNCT},
",": {POS: PUNCT},
"-LRB-": {POS: PUNCT},
"-RRB-": {POS: PUNCT},
"``": {POS: PUNCT},
'""': {POS: PUNCT},
"''": {POS: PUNCT},
":": {POS: PUNCT},
"$": {POS: SYM, "Other": {"SymType": "currency"}},
"#": {POS: SYM, "Other": {"SymType": "numbersign"}},
"AFX": {POS: ADJ, "Hyph": "yes"},
"CC": {POS: CCONJ, "ConjType": "coor"},
"CD": {POS: NUM, "NumType": "card"},
"$": {POS: SYM},
"#": {POS: SYM},
"AFX": {POS: ADJ},
"CC": {POS: CCONJ},
"CD": {POS: NUM},
"DT": {POS: DET},
"EX": {POS: ADV, "AdvType": "ex"},
"FW": {POS: X, "Foreign": "yes"},
"HYPH": {POS: PUNCT, "PunctType": "dash"},
"EX": {POS: ADV},
"FW": {POS: X},
"HYPH": {POS: PUNCT},
"IN": {POS: ADP},
"JJ": {POS: ADJ, "Degree": "pos"},
"JJR": {POS: ADJ, "Degree": "comp"},
"JJS": {POS: ADJ, "Degree": "sup"},
"LS": {POS: PUNCT, "NumType": "ord"},
"MD": {POS: VERB, "VerbType": "mod"},
"JJ": {POS: ADJ},
"JJR": {POS: ADJ},
"JJS": {POS: ADJ},
"LS": {POS: PUNCT},
"MD": {POS: VERB},
"NIL": {POS: ""},
"NN": {POS: NOUN, "Number": "sing"},
"NNP": {POS: PROPN, "NounType": "prop", "Number": "sing"},
"NNPS": {POS: PROPN, "NounType": "prop", "Number": "plur"},
"NNS": {POS: NOUN, "Number": "plur"},
"PDT": {POS: ADJ, "AdjType": "pdt", "PronType": "prn"},
"POS": {POS: PART, "Poss": "yes"},
"PRP": {POS: PRON, "PronType": "prs"},
"PRP$": {POS: ADJ, "PronType": "prs", "Poss": "yes"},
"RB": {POS: ADV, "Degree": "pos"},
"RBR": {POS: ADV, "Degree": "comp"},
"RBS": {POS: ADV, "Degree": "sup"},
"NN": {POS: NOUN},
"NNP": {POS: PROPN},
"NNPS": {POS: PROPN},
"NNS": {POS: NOUN},
"PDT": {POS: ADJ},
"POS": {POS: PART},
"PRP": {POS: PRON},
"PRP$": {POS: ADJ},
"RB": {POS: ADV},
"RBR": {POS: ADV},
"RBS": {POS: ADV},
"RP": {POS: PART},
"SP": {POS: SPACE},
"SYM": {POS: SYM},
"TO": {POS: PART, "PartType": "inf", "VerbForm": "inf"},
"TO": {POS: PART},
"UH": {POS: INTJ},
"VB": {POS: VERB, "VerbForm": "inf"},
"VBD": {POS: VERB, "VerbForm": "fin", "Tense": "past"},
"VBG": {POS: VERB, "VerbForm": "part", "Tense": "pres", "Aspect": "prog"},
"VBN": {POS: VERB, "VerbForm": "part", "Tense": "past", "Aspect": "perf"},
"VBP": {POS: VERB, "VerbForm": "fin", "Tense": "pres"},
"VBZ": {
POS: VERB,
"VerbForm": "fin",
"Tense": "pres",
"Number": "sing",
"Person": 3,
},
"WDT": {POS: ADJ, "PronType": "int|rel"},
"WP": {POS: NOUN, "PronType": "int|rel"},
"WP$": {POS: ADJ, "Poss": "yes", "PronType": "int|rel"},
"WRB": {POS: ADV, "PronType": "int|rel"},
"VB": {POS: VERB},
"VBD": {POS: VERB},
"VBG": {POS: VERB},
"VBN": {POS: VERB},
"VBP": {POS: VERB},
"VBZ": {POS: VERB},
"WDT": {POS: ADJ},
"WP": {POS: NOUN},
"WP$": {POS: ADJ},
"WRB": {POS: ADV},
"ADD": {POS: X},
"NFP": {POS: PUNCT},
"GW": {POS: X},