zh_core_web_md / meta.json
adrianeboyd's picture
Update spaCy pipeline
81b478c
{
"lang":"zh",
"name":"core_web_md",
"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":300,
"vectors":20000,
"keys":500000,
"name":"zh_vectors"
},
"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":0.9003849582,
"sents_p":0.7889229659,
"sents_r":0.7279840186,
"sents_f":0.7572294372,
"dep_uas":0.7049895344,
"dep_las":0.652241773,
"dep_las_per_type":{
"dep":{
"p":0.480506402,
"r":0.3374760028,
"f":0.3964862298
},
"case":{
"p":0.8137318047,
"r":0.7658826382,
"f":0.7890825058
},
"nmod:tmod":{
"p":0.7230971129,
"r":0.7496598639,
"f":0.7361389446
},
"nummod":{
"p":0.8259067358,
"r":0.5309793471,
"f":0.6463909165
},
"mark:clf":{
"p":0.9348494161,
"r":0.5673256248,
"f":0.7061281337
},
"auxpass":{
"p":0.8641304348,
"r":0.8594594595,
"f":0.8617886179
},
"nsubj":{
"p":0.7849376823,
"r":0.7271833927,
"f":0.7549575974
},
"acl":{
"p":0.6644606221,
"r":0.556849695,
"f":0.605914303
},
"advmod":{
"p":0.820278834,
"r":0.7336204942,
"f":0.7745332695
},
"mark":{
"p":0.7400654511,
"r":0.6936897458,
"f":0.7161275729
},
"xcomp":{
"p":0.7865168539,
"r":0.6840390879,
"f":0.7317073171
},
"nmod:assmod":{
"p":0.7600130251,
"r":0.7264239029,
"f":0.7428389561
},
"det":{
"p":0.8406148867,
"r":0.6086701816,
"f":0.706082229
},
"amod":{
"p":0.7720254314,
"r":0.6677140613,
"f":0.7160909857
},
"nmod:prep":{
"p":0.6991273997,
"r":0.6058681186,
"f":0.6491654513
},
"root":{
"p":0.7380861609,
"r":0.6445813218,
"f":0.688172043
},
"aux:prtmod":{
"p":0.9031007752,
"r":0.8321428571,
"f":0.8661710037
},
"compound:nn":{
"p":0.733790195,
"r":0.7065989848,
"f":0.7199379364
},
"dobj":{
"p":0.800386349,
"r":0.7364834839,
"f":0.7671063797
},
"ccomp":{
"p":0.6472945892,
"r":0.6279160187,
"f":0.637458062
},
"advmod:rcomp":{
"p":0.8140243902,
"r":0.7396121884,
"f":0.7750362845
},
"nmod:topic":{
"p":0.351758794,
"r":0.2272727273,
"f":0.2761341223
},
"cop":{
"p":0.7524429967,
"r":0.5945945946,
"f":0.6642703091
},
"discourse":{
"p":0.5552434457,
"r":0.4892739274,
"f":0.5201754386
},
"neg":{
"p":0.8400597907,
"r":0.6682520809,
"f":0.7443708609
},
"aux:modal":{
"p":0.8646616541,
"r":0.8324715615,
"f":0.8482613277
},
"nmod":{
"p":0.7028753994,
"r":0.5970149254,
"f":0.6456346295
},
"aux:ba":{
"p":0.8453038674,
"r":0.8138297872,
"f":0.8292682927
},
"advmod:loc":{
"p":0.577689243,
"r":0.4302670623,
"f":0.4931972789
},
"aux:asp":{
"p":0.9067656766,
"r":0.8763955343,
"f":0.8913219789
},
"conj":{
"p":0.4907251265,
"r":0.4950850662,
"f":0.492895455
},
"nsubjpass":{
"p":0.7954545455,
"r":0.7,
"f":0.7446808511
},
"compound:vc":{
"p":0.4725274725,
"r":0.4455958549,
"f":0.4586666667
},
"advcl:loc":{
"p":0.4461538462,
"r":0.4142857143,
"f":0.4296296296
},
"cc":{
"p":0.7127962085,
"r":0.6672582076,
"f":0.6892758937
},
"advmod:dvp":{
"p":0.8307692308,
"r":0.6708074534,
"f":0.7422680412
},
"name":{
"p":0.619047619,
"r":0.4814814815,
"f":0.5416666667
},
"appos":{
"p":0.8877805486,
"r":0.8183908046,
"f":0.8516746411
},
"nmod:poss":{
"p":0.65625,
"r":0.4666666667,
"f":0.5454545455
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.7480314961,
"r":0.6375838926,
"f":0.6884057971
},
"parataxis:prnmod":{
"p":0.4857142857,
"r":0.1278195489,
"f":0.2023809524
},
"amod:ordmod":{
"p":0.5606060606,
"r":0.578125,
"f":0.5692307692
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.9285714286,
"r":0.9285714286,
"f":0.9285714286
}
},
"ents_p":0.7188227082,
"ents_r":0.679010989,
"ents_f":0.6983499096,
"ents_per_type":{
"DATE":{
"p":0.7758945386,
"r":0.8166501487,
"f":0.795750845
},
"GPE":{
"p":0.7566351777,
"r":0.8220918866,
"f":0.7880065589
},
"ORDINAL":{
"p":0.8764705882,
"r":0.7842105263,
"f":0.8277777778
},
"FAC":{
"p":0.4353741497,
"r":0.3440860215,
"f":0.3843843844
},
"PERSON":{
"p":0.7662082515,
"r":0.7538659794,
"f":0.7599870088
},
"ORG":{
"p":0.6975409836,
"r":0.6476407915,
"f":0.6716653512
},
"LOC":{
"p":0.4691780822,
"r":0.3682795699,
"f":0.4126506024
},
"QUANTITY":{
"p":0.7543859649,
"r":0.637037037,
"f":0.6907630522
},
"CARDINAL":{
"p":0.6059225513,
"r":0.5362903226,
"f":0.5689839572
},
"NORP":{
"p":0.6955128205,
"r":0.4558823529,
"f":0.5507614213
},
"WORK_OF_ART":{
"p":0.5921052632,
"r":0.3,
"f":0.3982300885
},
"TIME":{
"p":0.7452830189,
"r":0.7669902913,
"f":0.7559808612
},
"MONEY":{
"p":0.9322033898,
"r":0.8148148148,
"f":0.8695652174
},
"EVENT":{
"p":0.5625,
"r":0.4632352941,
"f":0.5080645161
},
"PERCENT":{
"p":0.8313253012,
"r":0.8313253012,
"f":0.8313253012
},
"PRODUCT":{
"p":0.125,
"r":0.0204081633,
"f":0.0350877193
},
"LAW":{
"p":0.5,
"r":0.2333333333,
"f":0.3181818182
},
"LANGUAGE":{
"p":0.5,
"r":0.7777777778,
"f":0.6086956522
}
},
"speed":5968.354118929
},
"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":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
"spacy-pkuseg>=0.0.27,<0.1.0"
]
}