zh_core_web_trf / meta.json
adrianeboyd's picture
Update spaCy pipeline
0413247
{
"lang":"zh",
"name":"core_web_trf",
"version":"3.4.0",
"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":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"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":0.9237103231,
"sents_p":0.6885372443,
"sents_r":0.5939736974,
"sents_f":0.6377692376,
"dep_uas":0.7641386414,
"dep_las":0.724427042,
"dep_las_per_type":{
"dep":{
"p":0.556125806,
"r":0.4269980802,
"f":0.4830818473
},
"case":{
"p":0.9095206829,
"r":0.8397187197,
"f":0.8732270062
},
"nmod:tmod":{
"p":0.801082544,
"r":0.8054421769,
"f":0.803256445
},
"nummod":{
"p":0.8936170213,
"r":0.5876082612,
"f":0.7090032154
},
"mark:clf":{
"p":0.9504950495,
"r":0.572920552,
"f":0.7149173842
},
"auxpass":{
"p":0.9293478261,
"r":0.9243243243,
"f":0.9268292683
},
"nsubj":{
"p":0.8697112156,
"r":0.7953568358,
"f":0.8308738612
},
"acl":{
"p":0.8118811881,
"r":0.7276760954,
"f":0.7674758701
},
"advmod":{
"p":0.8822219311,
"r":0.7633189753,
"f":0.8184746278
},
"mark":{
"p":0.8395604396,
"r":0.8369851008,
"f":0.8382707922
},
"xcomp":{
"p":0.8200757576,
"r":0.7052117264,
"f":0.7583187391
},
"nmod:assmod":{
"p":0.8556113903,
"r":0.7948957361,
"f":0.8241368183
},
"det":{
"p":0.8923076923,
"r":0.6455770357,
"f":0.7491502379
},
"amod":{
"p":0.8492438563,
"r":0.7058130401,
"f":0.7709137709
},
"nmod:prep":{
"p":0.8267821452,
"r":0.7507562008,
"f":0.7869372226
},
"root":{
"p":0.7861788618,
"r":0.643915432,
"f":0.7079710808
},
"aux:prtmod":{
"p":0.9291338583,
"r":0.8428571429,
"f":0.8838951311
},
"compound:nn":{
"p":0.8028863076,
"r":0.7719120135,
"f":0.787094548
},
"dobj":{
"p":0.9105064743,
"r":0.8228410606,
"f":0.8644568939
},
"ccomp":{
"p":0.783817952,
"r":0.7231726283,
"f":0.7522750253
},
"advmod:rcomp":{
"p":0.8445747801,
"r":0.7977839335,
"f":0.8205128205
},
"nmod:topic":{
"p":0.4741641337,
"r":0.5064935065,
"f":0.4897959184
},
"cop":{
"p":0.8486672399,
"r":0.6351351351,
"f":0.7265366213
},
"discourse":{
"p":0.5922939068,
"r":0.545379538,
"f":0.5678694158
},
"neg":{
"p":0.8825347759,
"r":0.6789536266,
"f":0.7674731183
},
"aux:modal":{
"p":0.8969631236,
"r":0.8552223371,
"f":0.8755955532
},
"nmod":{
"p":0.8,
"r":0.7598371777,
"f":0.779401531
},
"aux:ba":{
"p":0.9162011173,
"r":0.8723404255,
"f":0.89373297
},
"advmod:loc":{
"p":0.792,
"r":0.587537092,
"f":0.6746166951
},
"aux:asp":{
"p":0.9298986486,
"r":0.8779904306,
"f":0.9031993437
},
"conj":{
"p":0.615168012,
"r":0.6194706994,
"f":0.6173118583
},
"nsubjpass":{
"p":0.8723404255,
"r":0.82,
"f":0.8453608247
},
"compound:vc":{
"p":0.5339805825,
"r":0.5699481865,
"f":0.5513784461
},
"advcl:loc":{
"p":0.6567164179,
"r":0.6285714286,
"f":0.6423357664
},
"cc":{
"p":0.7996306556,
"r":0.7684117125,
"f":0.7837104072
},
"advmod:dvp":{
"p":0.8518518519,
"r":0.7142857143,
"f":0.777027027
},
"amod:ordmod":{
"p":0.703125,
"r":0.703125,
"f":0.703125
},
"appos":{
"p":0.9509803922,
"r":0.891954023,
"f":0.9205219454
},
"nmod:poss":{
"p":0.8230088496,
"r":0.6888888889,
"f":0.75
},
"name":{
"p":0.6513761468,
"r":0.5259259259,
"f":0.5819672131
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.8264150943,
"r":0.7348993289,
"f":0.7779751332
},
"parataxis:prnmod":{
"p":0.2475247525,
"r":0.1879699248,
"f":0.2136752137
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.8965517241,
"r":0.9285714286,
"f":0.9122807018
}
},
"ents_p":0.6807715613,
"ents_r":0.7407692308,
"ents_f":0.7095042627,
"ents_per_type":{
"DATE":{
"p":0.7026116259,
"r":0.8265609514,
"f":0.7595628415
},
"GPE":{
"p":0.8069756331,
"r":0.8255131965,
"f":0.816139164
},
"ORDINAL":{
"p":0.8514285714,
"r":0.7842105263,
"f":0.8164383562
},
"FAC":{
"p":0.4751381215,
"r":0.4623655914,
"f":0.4686648501
},
"ORG":{
"p":0.7506033789,
"r":0.7100456621,
"f":0.7297614392
},
"LOC":{
"p":0.1955867603,
"r":0.5241935484,
"f":0.2848794741
},
"NORP":{
"p":0.6170212766,
"r":0.6092436975,
"f":0.6131078224
},
"QUANTITY":{
"p":0.615942029,
"r":0.6296296296,
"f":0.6227106227
},
"PERSON":{
"p":0.8742783836,
"r":0.8782216495,
"f":0.8762455802
},
"CARDINAL":{
"p":0.560111836,
"r":0.6058467742,
"f":0.5820823245
},
"TIME":{
"p":0.7314814815,
"r":0.7669902913,
"f":0.7488151659
},
"WORK_OF_ART":{
"p":0.4108527132,
"r":0.3533333333,
"f":0.3799283154
},
"MONEY":{
"p":0.873015873,
"r":0.8148148148,
"f":0.8429118774
},
"EVENT":{
"p":0.5945945946,
"r":0.6470588235,
"f":0.6197183099
},
"PRODUCT":{
"p":0.375,
"r":0.1836734694,
"f":0.2465753425
},
"PERCENT":{
"p":0.843373494,
"r":0.843373494,
"f":0.843373494
},
"LAW":{
"p":0.3958333333,
"r":0.3166666667,
"f":0.3518518519
},
"LANGUAGE":{
"p":0.75,
"r":1.0,
"f":0.8571428571
}
},
"speed":4551.3152436145
},
"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"
]
}