zh_core_web_trf / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
5c423e0
raw history blame
No virus
10.1 kB
{
"lang":"zh",
"name":"core_web_trf",
"version":"3.2.0",
"description":"Chinese transformer pipeline (bert-base-chinese). Components: transformer, tagger, parser, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.2.0,<3.3.0",
"spacy_git_version":"bb26550e2",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"transformer":[
],
"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"
],
"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":[
"transformer",
"tagger",
"parser",
"attribute_ruler",
"ner"
],
"components":[
"transformer",
"tagger",
"parser",
"attribute_ruler",
"ner"
],
"disabled":[
],
"performance":{
"token_acc":0.9788303388,
"token_p":0.9458325855,
"token_r":0.9136060443,
"token_f":0.9294400505,
"tag_acc":0.9247167985,
"sents_p":0.7110739502,
"sents_r":0.6370900616,
"sents_f":0.67205198,
"dep_uas":0.7683558244,
"dep_las":0.7307018312,
"dep_las_per_type":{
"dep":{
"p":0.5656512605,
"r":0.4352834192,
"f":0.4919773882
},
"case":{
"p":0.9131065401,
"r":0.8395974782,
"f":0.8748105104
},
"nmod:tmod":{
"p":0.8136054422,
"r":0.8136054422,
"f":0.8136054422
},
"nummod":{
"p":0.9011213048,
"r":0.5889407062,
"f":0.7123287671
},
"mark:clf":{
"p":0.9499691167,
"r":0.5736665423,
"f":0.7153488372
},
"auxpass":{
"p":0.9293478261,
"r":0.9243243243,
"f":0.9268292683
},
"nsubj":{
"p":0.8800107614,
"r":0.803586783,
"f":0.8400642055
},
"acl":{
"p":0.8209331652,
"r":0.7221297837,
"f":0.7683682502
},
"advmod":{
"p":0.8834787137,
"r":0.7692133303,
"f":0.822395928
},
"mark":{
"p":0.8492417484,
"r":0.8343558282,
"f":0.8417329797
},
"xcomp":{
"p":0.8368522073,
"r":0.7100977199,
"f":0.7682819383
},
"nmod:assmod":{
"p":0.8744897959,
"r":0.8001867414,
"f":0.8356899074
},
"det":{
"p":0.8905872888,
"r":0.6485061511,
"f":0.7505084746
},
"amod":{
"p":0.8427987279,
"r":0.7285938727,
"f":0.7815462397
},
"nmod:prep":{
"p":0.8286297178,
"r":0.7371445856,
"f":0.780214503
},
"root":{
"p":0.792271479,
"r":0.6723822207,
"f":0.727420081
},
"aux:prtmod":{
"p":0.9251968504,
"r":0.8392857143,
"f":0.8801498127
},
"compound:nn":{
"p":0.8133166279,
"r":0.7688663283,
"f":0.7904670784
},
"dobj":{
"p":0.9164218087,
"r":0.8315805066,
"f":0.8719422226
},
"ccomp":{
"p":0.7944862155,
"r":0.7395023328,
"f":0.7660088602
},
"advmod:rcomp":{
"p":0.8541033435,
"r":0.7783933518,
"f":0.8144927536
},
"nmod:topic":{
"p":0.5104166667,
"r":0.4772727273,
"f":0.4932885906
},
"cop":{
"p":0.8533218292,
"r":0.6364221364,
"f":0.7290821968
},
"discourse":{
"p":0.6257833483,
"r":0.5767326733,
"f":0.6002576213
},
"neg":{
"p":0.898089172,
"r":0.6706302021,
"f":0.7678692988
},
"aux:modal":{
"p":0.9086908691,
"r":0.854188211,
"f":0.8805970149
},
"nmod":{
"p":0.8080808081,
"r":0.7598371777,
"f":0.7832167832
},
"aux:ba":{
"p":0.9485714286,
"r":0.8829787234,
"f":0.914600551
},
"advmod:loc":{
"p":0.803030303,
"r":0.6290801187,
"f":0.7054908486
},
"aux:asp":{
"p":0.9346349745,
"r":0.8779904306,
"f":0.9054276316
},
"conj":{
"p":0.6249059443,
"r":0.6279773157,
"f":0.6264378654
},
"nsubjpass":{
"p":0.9302325581,
"r":0.8,
"f":0.8602150538
},
"compound:vc":{
"p":0.5380952381,
"r":0.585492228,
"f":0.5607940447
},
"advcl:loc":{
"p":0.7894736842,
"r":0.6428571429,
"f":0.7086614173
},
"cc":{
"p":0.8191287879,
"r":0.7675244011,
"f":0.7924874027
},
"advmod:dvp":{
"p":0.8731343284,
"r":0.7267080745,
"f":0.793220339
},
"amod:ordmod":{
"p":0.640625,
"r":0.640625,
"f":0.640625
},
"appos":{
"p":0.9443099274,
"r":0.8965517241,
"f":0.9198113208
},
"nmod:poss":{
"p":0.796460177,
"r":0.6666666667,
"f":0.7258064516
},
"name":{
"p":0.6635514019,
"r":0.5259259259,
"f":0.5867768595
},
"nsubj:xsubj":{
"p":0.25,
"r":0.1,
"f":0.1428571429
},
"nmod:range":{
"p":0.8365019011,
"r":0.7382550336,
"f":0.7843137255
},
"parataxis:prnmod":{
"p":0.3645833333,
"r":0.2631578947,
"f":0.3056768559
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.8965517241,
"r":0.9285714286,
"f":0.9122807018
}
},
"ents_p":0.746365105,
"ents_r":0.7615384615,
"ents_f":0.7538754419,
"ents_per_type":{
"DATE":{
"p":0.7673357664,
"r":0.8334985134,
"f":0.7990498812
},
"GPE":{
"p":0.7898259705,
"r":0.8651026393,
"f":0.8257522743
},
"ORDINAL":{
"p":0.8720930233,
"r":0.7894736842,
"f":0.8287292818
},
"FAC":{
"p":0.4685990338,
"r":0.5215053763,
"f":0.4936386768
},
"ORG":{
"p":0.749034749,
"r":0.7382039574,
"f":0.7435799157
},
"NORP":{
"p":0.6806930693,
"r":0.5777310924,
"f":0.625
},
"LOC":{
"p":0.5765765766,
"r":0.5161290323,
"f":0.5446808511
},
"QUANTITY":{
"p":0.6742424242,
"r":0.6592592593,
"f":0.6666666667
},
"PERSON":{
"p":0.8638871858,
"r":0.9078608247,
"f":0.8853283066
},
"CARDINAL":{
"p":0.6205821206,
"r":0.6018145161,
"f":0.6110542477
},
"TIME":{
"p":0.7630331754,
"r":0.7815533981,
"f":0.7721822542
},
"WORK_OF_ART":{
"p":0.4724409449,
"r":0.4,
"f":0.4332129964
},
"MONEY":{
"p":0.8615384615,
"r":0.8296296296,
"f":0.8452830189
},
"EVENT":{
"p":0.5757575758,
"r":0.6985294118,
"f":0.6312292359
},
"PERCENT":{
"p":0.7865168539,
"r":0.843373494,
"f":0.8139534884
},
"PRODUCT":{
"p":0.4814814815,
"r":0.2653061224,
"f":0.3421052632
},
"LAW":{
"p":0.3921568627,
"r":0.3333333333,
"f":0.3603603604
},
"LANGUAGE":{
"p":0.75,
"r":1.0,
"f":0.8571428571
}
},
"speed":4253.4050367787
},
"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"
},
{
"name":"bert-base-chinese",
"author":"Hugging Face",
"url":"https://huggingface.co/bert-base-chinese",
"license":""
}
],
"requirements":[
"spacy-transformers>=1.1.2,<1.2.0",
"spacy-pkuseg>=0.0.27,<0.1.0"
]
}