zh_core_web_sm / meta.json
osanseviero's picture
Update spaCy pipeline
1868f26
raw
history blame
9.81 kB
{
"lang":"zh",
"name":"core_web_sm",
"version":"3.1.0",
"description":"Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"[email protected]",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"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"
],
"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"
],
"senter":[
"I",
"S"
],
"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,
"tag_acc":0.8957464158,
"dep_uas":0.6965379684,
"dep_las":0.6426392548,
"ents_p":0.7224990884,
"ents_r":0.6531868132,
"ents_f":0.6860968431,
"sents_p":0.7817728729,
"sents_r":0.7311469952,
"sents_f":0.7556129032,
"speed":10175.5709293766,
"dep_las_per_type":{
"dep":{
"p":0.4702473498,
"r":0.3361624735,
"f":0.3920575065
},
"case":{
"p":0.8028549383,
"r":0.7569107662,
"f":0.7792061907
},
"nmod:tmod":{
"p":0.7231788079,
"r":0.7428571429,
"f":0.732885906
},
"nummod":{
"p":0.8233471074,
"r":0.5309793471,
"f":0.6456055083
},
"mark:clf":{
"p":0.9301898347,
"r":0.5665796345,
"f":0.7042188224
},
"auxpass":{
"p":0.8756756757,
"r":0.8756756757,
"f":0.8756756757
},
"nsubj":{
"p":0.771189813,
"r":0.7141628793,
"f":0.7415816327
},
"acl":{
"p":0.6791758646,
"r":0.5119245702,
"f":0.5838077166
},
"advmod":{
"p":0.8065869786,
"r":0.7189979596,
"f":0.7602780774
},
"mark":{
"p":0.7065868263,
"r":0.6722173532,
"f":0.6889737256
},
"xcomp":{
"p":0.7559198543,
"r":0.6758957655,
"f":0.7136715391
},
"nmod:assmod":{
"p":0.7642786398,
"r":0.7205104264,
"f":0.7417494393
},
"det":{
"p":0.8394160584,
"r":0.6063268893,
"f":0.7040816327
},
"amod":{
"p":0.7544338336,
"r":0.6516103692,
"f":0.6992623815
},
"nmod:prep":{
"p":0.7013125222,
"r":0.5980036298,
"f":0.6455510204
},
"root":{
"p":0.7283996995,
"r":0.6455801565,
"f":0.6844938664
},
"aux:prtmod":{
"p":0.890625,
"r":0.8142857143,
"f":0.8507462687
},
"compound:nn":{
"p":0.7243023667,
"r":0.6939086294,
"f":0.7087798133
},
"dobj":{
"p":0.780507386,
"r":0.7200414753,
"f":0.7490561677
},
"ccomp":{
"p":0.6268199234,
"r":0.6360808709,
"f":0.6314164415
},
"advmod:rcomp":{
"p":0.8096774194,
"r":0.6952908587,
"f":0.7481371088
},
"nmod:topic":{
"p":0.3686868687,
"r":0.237012987,
"f":0.2885375494
},
"cop":{
"p":0.7385620915,
"r":0.5817245817,
"f":0.6508279338
},
"discourse":{
"p":0.5540037244,
"r":0.4909240924,
"f":0.52055993
},
"neg":{
"p":0.823880597,
"r":0.6563614744,
"f":0.730641959
},
"aux:modal":{
"p":0.8563772776,
"r":0.8262668046,
"f":0.8410526316
},
"nmod":{
"p":0.7135761589,
"r":0.5848032564,
"f":0.6428038777
},
"aux:ba":{
"p":0.8087431694,
"r":0.7872340426,
"f":0.7978436658
},
"advmod:loc":{
"p":0.58203125,
"r":0.4421364985,
"f":0.502529511
},
"aux:asp":{
"p":0.9053941909,
"r":0.870015949,
"f":0.8873525824
},
"conj":{
"p":0.4784786642,
"r":0.4875236295,
"f":0.4829588015
},
"nsubjpass":{
"p":0.8292682927,
"r":0.68,
"f":0.7472527473
},
"compound:vc":{
"p":0.3876404494,
"r":0.3575129534,
"f":0.371967655
},
"advcl:loc":{
"p":0.5304347826,
"r":0.4357142857,
"f":0.4784313725
},
"cc":{
"p":0.6937618147,
"r":0.6512866016,
"f":0.6718535469
},
"advmod:dvp":{
"p":0.8114754098,
"r":0.6149068323,
"f":0.6996466431
},
"appos":{
"p":0.8778054863,
"r":0.8091954023,
"f":0.8421052632
},
"nmod:range":{
"p":0.6897810219,
"r":0.6342281879,
"f":0.6608391608
},
"nmod:poss":{
"p":0.6989247312,
"r":0.4814814815,
"f":0.5701754386
},
"name":{
"p":0.6391752577,
"r":0.4592592593,
"f":0.5344827586
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"parataxis:prnmod":{
"p":0.4516129032,
"r":0.1052631579,
"f":0.1707317073
},
"amod:ordmod":{
"p":0.6274509804,
"r":0.5,
"f":0.5565217391
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.8837209302,
"r":0.9047619048,
"f":0.8941176471
}
},
"ents_per_type":{
"DATE":{
"p":0.75,
"r":0.7849355798,
"f":0.7670702179
},
"GPE":{
"p":0.7579383341,
"r":0.8049853372,
"f":0.7807537331
},
"ORDINAL":{
"p":0.8603351955,
"r":0.8105263158,
"f":0.8346883469
},
"FAC":{
"p":0.4482758621,
"r":0.2795698925,
"f":0.3443708609
},
"ORG":{
"p":0.6875,
"r":0.602739726,
"f":0.6423357664
},
"QUANTITY":{
"p":0.7777777778,
"r":0.6222222222,
"f":0.6913580247
},
"PERSON":{
"p":0.8103932584,
"r":0.743556701,
"f":0.7755376344
},
"CARDINAL":{
"p":0.5814220183,
"r":0.5110887097,
"f":0.5439914163
},
"LOC":{
"p":0.5319148936,
"r":0.3360215054,
"f":0.4118616145
},
"NORP":{
"p":0.6774193548,
"r":0.4411764706,
"f":0.534351145
},
"WORK_OF_ART":{
"p":0.4520547945,
"r":0.22,
"f":0.2959641256
},
"TIME":{
"p":0.7438423645,
"r":0.7330097087,
"f":0.7383863081
},
"MONEY":{
"p":0.9292035398,
"r":0.7777777778,
"f":0.8467741935
},
"PERCENT":{
"p":0.8395061728,
"r":0.8192771084,
"f":0.8292682927
},
"EVENT":{
"p":0.6170212766,
"r":0.4264705882,
"f":0.5043478261
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.3043478261,
"r":0.1166666667,
"f":0.1686746988
},
"LANGUAGE":{
"p":0.5,
"r":0.5555555556,
"f":0.5263157895
}
}
},
"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"
]
}