zh_core_web_lg / meta.json
adrianeboyd's picture
Update spaCy pipeline
39450a8
{
"lang":"zh",
"name":"core_web_lg",
"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":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",
"_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":0.9033086963,
"sents_p":0.7805008945,
"sents_r":0.7263192942,
"sents_f":0.7524359748,
"dep_uas":0.7085620979,
"dep_las":0.6571012366,
"dep_las_per_type":{
"dep":{
"p":0.4891335027,
"r":0.3502071335,
"f":0.4081728788
},
"case":{
"p":0.8134414832,
"r":0.7660038797,
"f":0.7890103028
},
"nmod:tmod":{
"p":0.7418918919,
"r":0.7469387755,
"f":0.7444067797
},
"nummod":{
"p":0.8213914849,
"r":0.526982012,
"f":0.6420454545
},
"mark:clf":{
"p":0.9363525092,
"r":0.5706825811,
"f":0.7091541136
},
"auxpass":{
"p":0.8756756757,
"r":0.8756756757,
"f":0.8756756757
},
"nsubj":{
"p":0.7823165107,
"r":0.7292715883,
"f":0.7548633185
},
"acl":{
"p":0.68,
"r":0.5751525236,
"f":0.6231971154
},
"advmod":{
"p":0.8240446871,
"r":0.7357742009,
"f":0.7774118211
},
"mark":{
"p":0.7440559441,
"r":0.6993865031,
"f":0.7210300429
},
"xcomp":{
"p":0.7920433996,
"r":0.7133550489,
"f":0.7506426735
},
"nmod:assmod":{
"p":0.7618586641,
"r":0.7348272642,
"f":0.7480988593
},
"det":{
"p":0.8412570508,
"r":0.611599297,
"f":0.7082767978
},
"amod":{
"p":0.7733213159,
"r":0.6739984289,
"f":0.7202518363
},
"nmod:prep":{
"p":0.7058197303,
"r":0.6016333938,
"f":0.6495754409
},
"root":{
"p":0.7391222096,
"r":0.6504078575,
"f":0.6919330559
},
"aux:prtmod":{
"p":0.9265306122,
"r":0.8107142857,
"f":0.8647619048
},
"compound:nn":{
"p":0.7435532634,
"r":0.7074450085,
"f":0.7250498569
},
"dobj":{
"p":0.8111419703,
"r":0.7354466005,
"f":0.7714418894
},
"ccomp":{
"p":0.6647704185,
"r":0.6360808709,
"f":0.6501092788
},
"advmod:rcomp":{
"p":0.8328173375,
"r":0.7451523546,
"f":0.7865497076
},
"nmod:topic":{
"p":0.3902439024,
"r":0.2597402597,
"f":0.3118908382
},
"cop":{
"p":0.75951417,
"r":0.6036036036,
"f":0.6726425242
},
"discourse":{
"p":0.56545961,
"r":0.5024752475,
"f":0.5321100917
},
"neg":{
"p":0.8517397882,
"r":0.6694411415,
"f":0.7496671105
},
"aux:modal":{
"p":0.8658146965,
"r":0.8407445708,
"f":0.8530954879
},
"nmod":{
"p":0.699844479,
"r":0.6105834464,
"f":0.652173913
},
"aux:ba":{
"p":0.8,
"r":0.7872340426,
"f":0.7935656836
},
"advmod:loc":{
"p":0.6434108527,
"r":0.4925816024,
"f":0.5579831933
},
"aux:asp":{
"p":0.910373444,
"r":0.874800638,
"f":0.8922326149
},
"conj":{
"p":0.5032003012,
"r":0.5052930057,
"f":0.5042444822
},
"nsubjpass":{
"p":0.7857142857,
"r":0.66,
"f":0.7173913043
},
"compound:vc":{
"p":0.4411764706,
"r":0.4663212435,
"f":0.4534005038
},
"advcl:loc":{
"p":0.4962406015,
"r":0.4714285714,
"f":0.4835164835
},
"cc":{
"p":0.717535545,
"r":0.6716947649,
"f":0.6938588451
},
"advmod:dvp":{
"p":0.8548387097,
"r":0.6583850932,
"f":0.7438596491
},
"appos":{
"p":0.8962025316,
"r":0.8137931034,
"f":0.8530120482
},
"nmod:poss":{
"p":0.6931818182,
"r":0.4518518519,
"f":0.5470852018
},
"name":{
"p":0.6421052632,
"r":0.4518518519,
"f":0.5304347826
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.756,
"r":0.6342281879,
"f":0.6897810219
},
"parataxis:prnmod":{
"p":0.4705882353,
"r":0.1203007519,
"f":0.1916167665
},
"amod:ordmod":{
"p":0.6271186441,
"r":0.578125,
"f":0.6016260163
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.9277108434,
"r":0.9166666667,
"f":0.9221556886
}
},
"ents_p":0.7355275444,
"ents_r":0.6925274725,
"ents_f":0.7133801223,
"ents_per_type":{
"DATE":{
"p":0.774952919,
"r":0.8156590684,
"f":0.794785128
},
"GPE":{
"p":0.786340563,
"r":0.8328445748,
"f":0.8089247567
},
"ORDINAL":{
"p":0.8830409357,
"r":0.7947368421,
"f":0.836565097
},
"FAC":{
"p":0.4444444444,
"r":0.3870967742,
"f":0.4137931034
},
"ORG":{
"p":0.6987854251,
"r":0.6567732116,
"f":0.6771282856
},
"LOC":{
"p":0.5863192182,
"r":0.4838709677,
"f":0.530191458
},
"QUANTITY":{
"p":0.7592592593,
"r":0.6074074074,
"f":0.6748971193
},
"PERSON":{
"p":0.7900194426,
"r":0.7854381443,
"f":0.7877221325
},
"CARDINAL":{
"p":0.6115023474,
"r":0.5252016129,
"f":0.5650759219
},
"NORP":{
"p":0.7160120846,
"r":0.4978991597,
"f":0.5873605948
},
"TIME":{
"p":0.7475728155,
"r":0.7475728155,
"f":0.7475728155
},
"WORK_OF_ART":{
"p":0.5616438356,
"r":0.2733333333,
"f":0.3677130045
},
"MONEY":{
"p":0.9322033898,
"r":0.8148148148,
"f":0.8695652174
},
"EVENT":{
"p":0.6213592233,
"r":0.4705882353,
"f":0.5355648536
},
"PERCENT":{
"p":0.7444444444,
"r":0.8072289157,
"f":0.774566474
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.3636363636,
"r":0.1333333333,
"f":0.1951219512
},
"LANGUAGE":{
"p":0.6,
"r":0.6666666667,
"f":0.6315789474
}
},
"speed":6761.7357765667
},
"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"
]
}