zh_core_web_trf / meta.json
adrianeboyd's picture
Update spaCy pipeline
c70655e
{
"lang":"zh",
"name":"core_web_trf",
"version":"3.7.2",
"description":"Chinese transformer pipeline (Transformer(name='bert-base-chinese', piece_encoder='bert-wordpiece', stride=152, type='bert', width=768, window=208, vocab_size=21128)). Components: transformer, tagger, parser, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.7.0,<3.8.0",
"spacy_git_version":"4ec41e98f",
"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":0.9585384056,
"token_p":0.9458325855,
"token_r":0.9136060443,
"token_f":0.9294400505,
"tag_acc":0.9175332527,
"sents_p":0.7092434038,
"sents_r":0.6757116697,
"sents_f":0.6920716113,
"dep_uas":0.7572203056,
"dep_las":0.7145288854,
"dep_las_per_type":{
"dep":{
"p":0.5542676502,
"r":0.4251793473,
"f":0.4812167648
},
"case":{
"p":0.9020435069,
"r":0.8295344326,
"f":0.8642708268
},
"nmod:tmod":{
"p":0.7832446809,
"r":0.8013605442,
"f":0.7921990585
},
"nummod":{
"p":0.8815789474,
"r":0.5802798135,
"f":0.6998794697
},
"mark:clf":{
"p":0.9339393939,
"r":0.5747855278,
"f":0.711613946
},
"auxpass":{
"p":0.9095744681,
"r":0.9243243243,
"f":0.9168900804
},
"nsubj":{
"p":0.8642424242,
"r":0.7882324039,
"f":0.8244892715
},
"acl":{
"p":0.7845096814,
"r":0.6966167499,
"f":0.7379553467
},
"advmod":{
"p":0.868605557,
"r":0.7583314441,
"f":0.8097312999
},
"mark":{
"p":0.8348993289,
"r":0.8177037686,
"f":0.8262120877
},
"xcomp":{
"p":0.8014981273,
"r":0.6970684039,
"f":0.7456445993
},
"nmod:assmod":{
"p":0.8492146597,
"r":0.7572362278,
"f":0.8005923001
},
"det":{
"p":0.8788617886,
"r":0.633274751,
"f":0.7361252979
},
"amod":{
"p":0.8216442174,
"r":0.6948153967,
"f":0.7529261545
},
"nmod:prep":{
"p":0.8173109819,
"r":0.7226255293,
"f":0.7670573126
},
"root":{
"p":0.7621591746,
"r":0.6886965207,
"f":0.723567993
},
"aux:prtmod":{
"p":0.9551020408,
"r":0.8357142857,
"f":0.8914285714
},
"compound:nn":{
"p":0.7833185448,
"r":0.7468697124,
"f":0.764660026
},
"dobj":{
"p":0.8932703275,
"r":0.8120278477,
"f":0.8507138423
},
"ccomp":{
"p":0.7626977519,
"r":0.7122861586,
"f":0.7366304785
},
"advmod:rcomp":{
"p":0.8369230769,
"r":0.7534626039,
"f":0.7930029155
},
"nmod:topic":{
"p":0.4624505929,
"r":0.3798701299,
"f":0.4171122995
},
"cop":{
"p":0.8350515464,
"r":0.6254826255,
"f":0.7152317881
},
"discourse":{
"p":0.5836267606,
"r":0.547029703,
"f":0.5647359455
},
"neg":{
"p":0.8730650155,
"r":0.6706302021,
"f":0.7585743107
},
"aux:modal":{
"p":0.8915401302,
"r":0.8500517063,
"f":0.870301747
},
"nmod":{
"p":0.7740524781,
"r":0.7204884668,
"f":0.7463106114
},
"aux:ba":{
"p":0.9106145251,
"r":0.8670212766,
"f":0.8882833787
},
"advmod:loc":{
"p":0.7519379845,
"r":0.5756676558,
"f":0.6521008403
},
"aux:asp":{
"p":0.9163179916,
"r":0.8732057416,
"f":0.894242548
},
"conj":{
"p":0.6111647672,
"r":0.5981096408,
"f":0.6045667335
},
"nsubjpass":{
"p":0.9,
"r":0.72,
"f":0.8
},
"compound:vc":{
"p":0.4628820961,
"r":0.5492227979,
"f":0.5023696682
},
"advcl:loc":{
"p":0.6488549618,
"r":0.6071428571,
"f":0.6273062731
},
"cc":{
"p":0.7943396226,
"r":0.7471162378,
"f":0.7700045725
},
"advmod:dvp":{
"p":0.9212598425,
"r":0.7267080745,
"f":0.8125
},
"appos":{
"p":0.9382716049,
"r":0.8735632184,
"f":0.9047619048
},
"nmod:poss":{
"p":0.7280701754,
"r":0.6148148148,
"f":0.6666666667
},
"name":{
"p":0.6261682243,
"r":0.4962962963,
"f":0.5537190083
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.8098859316,
"r":0.7147651007,
"f":0.7593582888
},
"parataxis:prnmod":{
"p":0.3442622951,
"r":0.1578947368,
"f":0.2164948454
},
"amod:ordmod":{
"p":0.7547169811,
"r":0.625,
"f":0.6837606838
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.9277108434,
"r":0.9166666667,
"f":0.9221556886
}
},
"ents_p":0.7608897127,
"ents_r":0.7217582418,
"ents_f":0.7408075795,
"ents_per_type":{
"DATE":{
"p":0.7811607992,
"r":0.8136769078,
"f":0.7970873786
},
"GPE":{
"p":0.8325837081,
"r":0.8142717498,
"f":0.8233259204
},
"ORDINAL":{
"p":0.8488372093,
"r":0.7684210526,
"f":0.8066298343
},
"FAC":{
"p":0.3906976744,
"r":0.4516129032,
"f":0.4189526185
},
"LOC":{
"p":0.5012406948,
"r":0.5430107527,
"f":0.5212903226
},
"QUANTITY":{
"p":0.696,
"r":0.6444444444,
"f":0.6692307692
},
"ORG":{
"p":0.7461476075,
"r":0.700152207,
"f":0.7224185316
},
"PERSON":{
"p":0.8739386022,
"r":0.8621134021,
"f":0.8679857282
},
"CARDINAL":{
"p":0.6729088639,
"r":0.5433467742,
"f":0.6012269939
},
"NORP":{
"p":0.6961038961,
"r":0.5630252101,
"f":0.6225319396
},
"WORK_OF_ART":{
"p":0.5625,
"r":0.3,
"f":0.3913043478
},
"TIME":{
"p":0.7875647668,
"r":0.7378640777,
"f":0.7619047619
},
"MONEY":{
"p":0.9256198347,
"r":0.8296296296,
"f":0.875
},
"EVENT":{
"p":0.5430463576,
"r":0.6029411765,
"f":0.5714285714
},
"PERCENT":{
"p":0.869047619,
"r":0.8795180723,
"f":0.874251497
},
"PRODUCT":{
"p":0.3793103448,
"r":0.2244897959,
"f":0.2820512821
},
"LAW":{
"p":0.3571428571,
"r":0.25,
"f":0.2941176471
},
"LANGUAGE":{
"p":0.4666666667,
"r":0.7777777778,
"f":0.5833333333
}
},
"speed":2677.6055974261
},
"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-curated-transformers>=0.2.0,<0.3.0",
"spacy-pkuseg>=0.0.27,<0.1.0"
]
}