zh_core_web_sm / meta.json
Adriane Boyd
Update spaCy pipeline
c6b7012
raw
history blame
9.86 kB
{
"lang":"zh",
"name":"core_web_sm",
"version":"3.4.0",
"description":"Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"tok2vec":[
],
"tagger":[
"AD",
"AS",
"BA",
"CC",
"CD",
"CS",
"DEC",
"DEG",
"DER",
"DEV",
"DT",
"ETC",
"FW",
"IJ",
"INF",
"JJ",
"LB",
"LC",
"M",
"MSP",
"NN",
"NR",
"NT",
"OD",
"ON",
"P",
"PN",
"PU",
"SB",
"SP",
"URL",
"VA",
"VC",
"VE",
"VV",
"X",
"_SP"
],
"parser":[
"ROOT",
"acl",
"advcl:loc",
"advmod",
"advmod:dvp",
"advmod:loc",
"advmod:rcomp",
"amod",
"amod:ordmod",
"appos",
"aux:asp",
"aux:ba",
"aux:modal",
"aux:prtmod",
"auxpass",
"case",
"cc",
"ccomp",
"compound:nn",
"compound:vc",
"conj",
"cop",
"dep",
"det",
"discourse",
"dobj",
"etc",
"mark",
"mark:clf",
"name",
"neg",
"nmod",
"nmod:assmod",
"nmod:poss",
"nmod:prep",
"nmod:range",
"nmod:tmod",
"nmod:topic",
"nsubj",
"nsubj:xsubj",
"nsubjpass",
"nummod",
"parataxis:prnmod",
"punct",
"xcomp"
],
"attribute_ruler":[
],
"ner":[
"CARDINAL",
"DATE",
"EVENT",
"FAC",
"GPE",
"LANGUAGE",
"LAW",
"LOC",
"MONEY",
"NORP",
"ORDINAL",
"ORG",
"PERCENT",
"PERSON",
"PRODUCT",
"QUANTITY",
"TIME",
"WORK_OF_ART"
]
},
"pipeline":[
"tok2vec",
"tagger",
"parser",
"attribute_ruler",
"ner"
],
"components":[
"tok2vec",
"tagger",
"parser",
"senter",
"attribute_ruler",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9788303388,
"token_p":0.9458325855,
"token_r":0.9136060443,
"token_f":0.9294400505,
"tag_acc":0.893070133,
"sents_p":0.7772630078,
"sents_r":0.7261528217,
"sents_f":0.7508391428,
"dep_uas":0.6952509849,
"dep_las":0.6399561884,
"dep_las_per_type":{
"dep":{
"p":0.4732715609,
"r":0.3354551884,
"f":0.3926206244
},
"case":{
"p":0.8003097973,
"r":0.7516973812,
"f":0.7752422632
},
"nmod:tmod":{
"p":0.7309236948,
"r":0.7428571429,
"f":0.7368421053
},
"nummod":{
"p":0.8121775026,
"r":0.5243171219,
"f":0.6372469636
},
"mark:clf":{
"p":0.9270516717,
"r":0.5688176054,
"f":0.7050392973
},
"auxpass":{
"p":0.8655913978,
"r":0.8702702703,
"f":0.8679245283
},
"nsubj":{
"p":0.7646515312,
"r":0.7115833436,
"f":0.7371635808
},
"acl":{
"p":0.642,
"r":0.534109817,
"f":0.583106267
},
"advmod":{
"p":0.8104566849,
"r":0.7221718431,
"f":0.7637715039
},
"mark":{
"p":0.7050691244,
"r":0.6704645048,
"f":0.6873315364
},
"xcomp":{
"p":0.7522441652,
"r":0.6824104235,
"f":0.7156276687
},
"nmod:assmod":{
"p":0.7457293035,
"r":0.7065048242,
"f":0.7255873422
},
"det":{
"p":0.8379478827,
"r":0.6028119508,
"f":0.7011925043
},
"amod":{
"p":0.7527889335,
"r":0.6626080126,
"f":0.7048255693
},
"nmod:prep":{
"p":0.683988764,
"r":0.5892316999,
"f":0.6330841729
},
"root":{
"p":0.7289473684,
"r":0.6455801565,
"f":0.6847355875
},
"aux:prtmod":{
"p":0.89453125,
"r":0.8178571429,
"f":0.8544776119
},
"compound:nn":{
"p":0.7242711626,
"r":0.6978003384,
"f":0.710789383
},
"dobj":{
"p":0.7762623803,
"r":0.7081913791,
"f":0.7406661503
},
"ccomp":{
"p":0.6208661417,
"r":0.6131415241,
"f":0.6169796557
},
"advmod:rcomp":{
"p":0.8006134969,
"r":0.7229916898,
"f":0.7598253275
},
"nmod:topic":{
"p":0.2994923858,
"r":0.1915584416,
"f":0.2336633663
},
"cop":{
"p":0.7491776316,
"r":0.5862290862,
"f":0.6577617329
},
"discourse":{
"p":0.5658627087,
"r":0.50330033,
"f":0.5327510917
},
"neg":{
"p":0.8413173653,
"r":0.6682520809,
"f":0.7448641484
},
"aux:modal":{
"p":0.8640256959,
"r":0.8345398139,
"f":0.849026828
},
"nmod":{
"p":0.7037643208,
"r":0.5834464043,
"f":0.6379821958
},
"aux:ba":{
"p":0.8076923077,
"r":0.7819148936,
"f":0.7945945946
},
"advmod:loc":{
"p":0.6525423729,
"r":0.4569732938,
"f":0.537521815
},
"aux:asp":{
"p":0.8976705491,
"r":0.860446571,
"f":0.8786644951
},
"conj":{
"p":0.4690529456,
"r":0.4756143667,
"f":0.4723108692
},
"nsubjpass":{
"p":0.7619047619,
"r":0.64,
"f":0.6956521739
},
"compound:vc":{
"p":0.3825136612,
"r":0.3626943005,
"f":0.3723404255
},
"advcl:loc":{
"p":0.4836065574,
"r":0.4214285714,
"f":0.4503816794
},
"cc":{
"p":0.6941514861,
"r":0.6424134871,
"f":0.667281106
},
"advmod:dvp":{
"p":0.8823529412,
"r":0.652173913,
"f":0.75
},
"appos":{
"p":0.8714652956,
"r":0.7793103448,
"f":0.822815534
},
"name":{
"p":0.6195652174,
"r":0.4222222222,
"f":0.5022026432
},
"nmod:poss":{
"p":0.6547619048,
"r":0.4074074074,
"f":0.502283105
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.71484375,
"r":0.6140939597,
"f":0.6606498195
},
"parataxis:prnmod":{
"p":0.4358974359,
"r":0.1278195489,
"f":0.1976744186
},
"amod:ordmod":{
"p":0.649122807,
"r":0.578125,
"f":0.6115702479
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.8837209302,
"r":0.9047619048,
"f":0.8941176471
}
},
"ents_p":0.720477234,
"ents_r":0.6503296703,
"ents_f":0.6836086404,
"ents_per_type":{
"TIME":{
"p":0.7403846154,
"r":0.7475728155,
"f":0.7439613527
},
"GPE":{
"p":0.7642691415,
"r":0.8049853372,
"f":0.784099024
},
"ORDINAL":{
"p":0.8587570621,
"r":0.8,
"f":0.8283378747
},
"FAC":{
"p":0.4375,
"r":0.3010752688,
"f":0.3566878981
},
"DATE":{
"p":0.7596606975,
"r":0.7988107037,
"f":0.7787439614
},
"ORG":{
"p":0.6818950931,
"r":0.6133942161,
"f":0.6458333333
},
"QUANTITY":{
"p":0.7766990291,
"r":0.5925925926,
"f":0.6722689076
},
"PERSON":{
"p":0.7967072298,
"r":0.7171391753,
"f":0.7548321465
},
"CARDINAL":{
"p":0.5830429733,
"r":0.5060483871,
"f":0.5418240691
},
"LOC":{
"p":0.5061728395,
"r":0.3306451613,
"f":0.4
},
"NORP":{
"p":0.6578947368,
"r":0.4201680672,
"f":0.5128205128
},
"WORK_OF_ART":{
"p":0.487804878,
"r":0.2666666667,
"f":0.3448275862
},
"MONEY":{
"p":0.9026548673,
"r":0.7555555556,
"f":0.8225806452
},
"EVENT":{
"p":0.6483516484,
"r":0.4338235294,
"f":0.5198237885
},
"PERCENT":{
"p":0.8734177215,
"r":0.8313253012,
"f":0.8518518519
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.3076923077,
"r":0.0666666667,
"f":0.1095890411
},
"LANGUAGE":{
"p":0.5555555556,
"r":0.5555555556,
"f":0.5555555556
}
},
"speed":8841.6188314329
},
"sources":[
{
"name":"OntoNotes 5",
"url":"https://catalog.ldc.upenn.edu/LDC2013T19",
"license":"commercial (licensed by Explosion)",
"author":"Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston"
},
{
"name":"CoreNLP Universal Dependencies Converter",
"url":"https://nlp.stanford.edu/software/stanford-dependencies.html",
"author":"Stanford NLP Group",
"license":"Citation provided for reference, no code packaged with model"
}
],
"requirements":[
"spacy-pkuseg>=0.0.27,<0.1.0"
]
}