zh_core_web_sm / meta.json
adrianeboyd's picture
Update spaCy pipeline
e24daa3
{
"lang":"zh",
"name":"core_web_sm",
"version":"3.7.0",
"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":">=3.7.0,<3.8.0",
"spacy_git_version":"6b4f77441",
"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":0.9585384056,
"token_p":0.9458325855,
"token_r":0.9136060443,
"token_f":0.9294400505,
"tag_acc":0.8933253054,
"sents_p":0.7785115117,
"sents_r":0.7261528217,
"sents_f":0.7514211886,
"dep_uas":0.6960047338,
"dep_las":0.640776699,
"dep_las_per_type":{
"dep":{
"p":0.4694362848,
"r":0.3390926543,
"f":0.3937580664
},
"case":{
"p":0.8000770911,
"r":0.754970902,
"f":0.7768698147
},
"nmod:tmod":{
"p":0.7228915663,
"r":0.7346938776,
"f":0.7287449393
},
"nummod":{
"p":0.8084449022,
"r":0.5229846769,
"f":0.6351132686
},
"mark:clf":{
"p":0.9387755102,
"r":0.5662066393,
"f":0.7063750582
},
"auxpass":{
"p":0.8602150538,
"r":0.8648648649,
"f":0.8625336927
},
"nsubj":{
"p":0.7660695469,
"r":0.7144085493,
"f":0.7393376978
},
"acl":{
"p":0.6482479784,
"r":0.5335551858,
"f":0.5853361728
},
"advmod":{
"p":0.8146723099,
"r":0.7200181365,
"f":0.7644262591
},
"mark":{
"p":0.7090825265,
"r":0.6739702016,
"f":0.691080656
},
"xcomp":{
"p":0.7771639042,
"r":0.6872964169,
"f":0.7294727744
},
"nmod:assmod":{
"p":0.7495088409,
"r":0.7124183007,
"f":0.7304930589
},
"det":{
"p":0.8434712084,
"r":0.6092560047,
"f":0.7074829932
},
"amod":{
"p":0.7395555556,
"r":0.6535742341,
"f":0.693911593
},
"nmod:prep":{
"p":0.6834329933,
"r":0.5877192982,
"f":0.6319726785
},
"root":{
"p":0.7319140919,
"r":0.6467454636,
"f":0.686699072
},
"aux:prtmod":{
"p":0.890625,
"r":0.8142857143,
"f":0.8507462687
},
"compound:nn":{
"p":0.7195207893,
"r":0.6910321489,
"f":0.7049887796
},
"dobj":{
"p":0.7825518706,
"r":0.7095245149,
"f":0.7442510876
},
"ccomp":{
"p":0.6276764473,
"r":0.615474339,
"f":0.6215155084
},
"advmod:rcomp":{
"p":0.7747747748,
"r":0.7146814404,
"f":0.7435158501
},
"nmod:topic":{
"p":0.36,
"r":0.2337662338,
"f":0.2834645669
},
"cop":{
"p":0.7549833887,
"r":0.5849420849,
"f":0.659173314
},
"discourse":{
"p":0.5559599636,
"r":0.5041254125,
"f":0.5287754219
},
"neg":{
"p":0.8306092125,
"r":0.6646848989,
"f":0.7384412153
},
"aux:modal":{
"p":0.8569903949,
"r":0.8304033092,
"f":0.843487395
},
"nmod":{
"p":0.7133333333,
"r":0.5807327001,
"f":0.6402393418
},
"aux:ba":{
"p":0.7857142857,
"r":0.7606382979,
"f":0.772972973
},
"advmod:loc":{
"p":0.5772357724,
"r":0.4213649852,
"f":0.487135506
},
"aux:asp":{
"p":0.9117647059,
"r":0.86523126,
"f":0.887888707
},
"conj":{
"p":0.4801886792,
"r":0.4810964083,
"f":0.4806421152
},
"nsubjpass":{
"p":0.8222222222,
"r":0.74,
"f":0.7789473684
},
"compound:vc":{
"p":0.3827160494,
"r":0.3212435233,
"f":0.3492957746
},
"advcl:loc":{
"p":0.4015151515,
"r":0.3785714286,
"f":0.3897058824
},
"cc":{
"p":0.7023474178,
"r":0.6637089618,
"f":0.6824817518
},
"advmod:dvp":{
"p":0.796875,
"r":0.6335403727,
"f":0.7058823529
},
"appos":{
"p":0.8678304239,
"r":0.8,
"f":0.8325358852
},
"nmod:poss":{
"p":0.623655914,
"r":0.4296296296,
"f":0.5087719298
},
"name":{
"p":0.6,
"r":0.4444444444,
"f":0.5106382979
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.7287449393,
"r":0.6040268456,
"f":0.6605504587
},
"parataxis:prnmod":{
"p":0.3235294118,
"r":0.0827067669,
"f":0.1317365269
},
"amod:ordmod":{
"p":0.6315789474,
"r":0.5625,
"f":0.5950413223
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.8953488372,
"r":0.9166666667,
"f":0.9058823529
}
},
"ents_p":0.7203462148,
"ents_r":0.6493406593,
"ents_f":0.6830029475,
"ents_per_type":{
"TIME":{
"p":0.7368421053,
"r":0.7475728155,
"f":0.7421686747
},
"GPE":{
"p":0.7551676619,
"r":0.8035190616,
"f":0.778593417
},
"ORDINAL":{
"p":0.8555555556,
"r":0.8105263158,
"f":0.8324324324
},
"FAC":{
"p":0.4132231405,
"r":0.2688172043,
"f":0.325732899
},
"ORG":{
"p":0.6965998256,
"r":0.6080669711,
"f":0.6493295408
},
"DATE":{
"p":0.7602283539,
"r":0.7918731417,
"f":0.7757281553
},
"QUANTITY":{
"p":0.7545454545,
"r":0.6148148148,
"f":0.6775510204
},
"PERSON":{
"p":0.796886058,
"r":0.7255154639,
"f":0.7595278246
},
"LOC":{
"p":0.5333333333,
"r":0.3440860215,
"f":0.4183006536
},
"CARDINAL":{
"p":0.585106383,
"r":0.4989919355,
"f":0.5386289445
},
"NORP":{
"p":0.6765676568,
"r":0.4306722689,
"f":0.5263157895
},
"WORK_OF_ART":{
"p":0.4545454545,
"r":0.2333333333,
"f":0.3083700441
},
"MONEY":{
"p":0.9115044248,
"r":0.762962963,
"f":0.8306451613
},
"EVENT":{
"p":0.5666666667,
"r":0.375,
"f":0.4513274336
},
"PERCENT":{
"p":0.8313253012,
"r":0.8313253012,
"f":0.8313253012
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LANGUAGE":{
"p":0.4545454545,
"r":0.5555555556,
"f":0.5
},
"LAW":{
"p":0.4090909091,
"r":0.15,
"f":0.2195121951
}
},
"speed":6362.4196317694
},
"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"
]
}