zh_core_web_lg / meta.json
EC2 Default User
Update spaCy pipeline
f471992
raw
history blame
10 kB
{
"lang":"zh",
"name":"core_web_lg",
"version":"3.3.0",
"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":">=3.3.0.dev0,<3.4.0",
"spacy_git_version":"849bef2de",
"vectors":{
"width":300,
"vectors":500000,
"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"
],
"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":0.9788303388,
"token_p":0.9458325855,
"token_r":0.9136060443,
"token_f":0.9294400505,
"tag_acc":0.903399232,
"sents_p":0.7851653262,
"sents_r":0.7313134676,
"sents_f":0.757283227,
"dep_uas":0.708630098,
"dep_las":0.6570108094,
"dep_las_per_type":{
"dep":{
"p":0.4873308379,
"r":0.3420228352,
"f":0.4019473965
},
"case":{
"p":0.8121243126,
"r":0.7698836081,
"f":0.7904400324
},
"nmod:tmod":{
"p":0.7419786096,
"r":0.7551020408,
"f":0.7484828051
},
"nummod":{
"p":0.8179043744,
"r":0.5356429047,
"f":0.6473429952
},
"mark:clf":{
"p":0.9362745098,
"r":0.5699365908,
"f":0.7085555298
},
"auxpass":{
"p":0.8617021277,
"r":0.8756756757,
"f":0.8686327078
},
"nsubj":{
"p":0.7863859092,
"r":0.7293944233,
"f":0.7568187612
},
"acl":{
"p":0.6861842105,
"r":0.5784803106,
"f":0.6277460126
},
"advmod":{
"p":0.8230973788,
"r":0.7367943777,
"f":0.7775584664
},
"mark":{
"p":0.7435536803,
"r":0.6950043821,
"f":0.7184597961
},
"xcomp":{
"p":0.7836363636,
"r":0.7019543974,
"f":0.7405498282
},
"nmod:assmod":{
"p":0.763022508,
"r":0.7385620915,
"f":0.7505930729
},
"det":{
"p":0.8353317346,
"r":0.6121851201,
"f":0.7065584855
},
"amod":{
"p":0.7771274201,
"r":0.6779261587,
"f":0.7241451647
},
"nmod:prep":{
"p":0.6958174905,
"r":0.608892922,
"f":0.6494595903
},
"root":{
"p":0.74281935,
"r":0.6544031963,
"f":0.6958137888
},
"aux:prtmod":{
"p":0.8976377953,
"r":0.8142857143,
"f":0.8539325843
},
"compound:nn":{
"p":0.7375549692,
"r":0.7094754653,
"f":0.7232427771
},
"dobj":{
"p":0.8049725541,
"r":0.7385572508,
"f":0.7703360371
},
"ccomp":{
"p":0.65,
"r":0.6318040435,
"f":0.6407728707
},
"advmod:rcomp":{
"p":0.8198757764,
"r":0.7313019391,
"f":0.7730600293
},
"nmod:topic":{
"p":0.3668122271,
"r":0.2727272727,
"f":0.312849162
},
"cop":{
"p":0.7520325203,
"r":0.5952380952,
"f":0.6645114943
},
"discourse":{
"p":0.572761194,
"r":0.5066006601,
"f":0.5376532399
},
"neg":{
"p":0.8438438438,
"r":0.6682520809,
"f":0.7458526875
},
"aux:modal":{
"p":0.862911796,
"r":0.8397104447,
"f":0.8511530398
},
"nmod":{
"p":0.7196850394,
"r":0.6200814111,
"f":0.666180758
},
"aux:ba":{
"p":0.8202247191,
"r":0.7765957447,
"f":0.7978142077
},
"advmod:loc":{
"p":0.6396761134,
"r":0.46884273,
"f":0.5410958904
},
"aux:asp":{
"p":0.9109816972,
"r":0.8732057416,
"f":0.8916938111
},
"conj":{
"p":0.5052874447,
"r":0.4967863894,
"f":0.5010008579
},
"nsubjpass":{
"p":0.8205128205,
"r":0.64,
"f":0.7191011236
},
"compound:vc":{
"p":0.4213483146,
"r":0.3886010363,
"f":0.4043126685
},
"advcl:loc":{
"p":0.5267175573,
"r":0.4928571429,
"f":0.5092250923
},
"cc":{
"p":0.7130600572,
"r":0.6637089618,
"f":0.6875
},
"advmod:dvp":{
"p":0.8536585366,
"r":0.652173913,
"f":0.7394366197
},
"appos":{
"p":0.8705035971,
"r":0.8344827586,
"f":0.8521126761
},
"nmod:poss":{
"p":0.6947368421,
"r":0.4888888889,
"f":0.5739130435
},
"name":{
"p":0.71,
"r":0.5259259259,
"f":0.6042553191
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.7354085603,
"r":0.6342281879,
"f":0.6810810811
},
"parataxis:prnmod":{
"p":0.4193548387,
"r":0.0977443609,
"f":0.1585365854
},
"amod:ordmod":{
"p":0.606557377,
"r":0.578125,
"f":0.592
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.8941176471,
"r":0.9047619048,
"f":0.899408284
}
},
"ents_p":0.7403037383,
"ents_r":0.6963736264,
"ents_f":0.7176670442,
"ents_per_type":{
"DATE":{
"p":0.7652011225,
"r":0.810703667,
"f":0.7872954764
},
"GPE":{
"p":0.7768142401,
"r":0.8318670577,
"f":0.8033986311
},
"ORDINAL":{
"p":0.8705882353,
"r":0.7789473684,
"f":0.8222222222
},
"FAC":{
"p":0.464516129,
"r":0.3870967742,
"f":0.42228739
},
"ORG":{
"p":0.7108042242,
"r":0.6659056317,
"f":0.6876227898
},
"LOC":{
"p":0.5685618729,
"r":0.4569892473,
"f":0.5067064083
},
"QUANTITY":{
"p":0.7663551402,
"r":0.6074074074,
"f":0.6776859504
},
"PERSON":{
"p":0.8168642951,
"r":0.7989690722,
"f":0.8078175896
},
"CARDINAL":{
"p":0.6218097448,
"r":0.5403225806,
"f":0.5782092772
},
"NORP":{
"p":0.701183432,
"r":0.4978991597,
"f":0.5823095823
},
"TIME":{
"p":0.7427184466,
"r":0.7427184466,
"f":0.7427184466
},
"WORK_OF_ART":{
"p":0.676056338,
"r":0.32,
"f":0.4343891403
},
"MONEY":{
"p":0.9411764706,
"r":0.8296296296,
"f":0.8818897638
},
"EVENT":{
"p":0.6082474227,
"r":0.4338235294,
"f":0.5064377682
},
"PERCENT":{
"p":0.8095238095,
"r":0.8192771084,
"f":0.8143712575
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.4230769231,
"r":0.1833333333,
"f":0.2558139535
},
"LANGUAGE":{
"p":0.6,
"r":0.6666666667,
"f":0.6315789474
}
},
"speed":7558.2542061289
},
"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"
]
}