zh_core_web_md / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
0afbbcc
raw
history blame
No virus
10 kB
{
"lang":"zh",
"name":"core_web_md",
"version":"3.1.0",
"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":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"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"
],
"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":0.9004973002,
"dep_uas":0.7076909586,
"dep_las":0.6551856356,
"ents_p":0.7220589964,
"ents_r":0.6751648352,
"ents_f":0.6978249759,
"sents_p":0.7859447831,
"sents_r":0.7298152156,
"sents_f":0.7568407423,
"speed":10063.789558808,
"dep_las_per_type":{
"dep":{
"p":0.4941927991,
"r":0.3439426089,
"f":0.4056002383
},
"case":{
"p":0.815348957,
"r":0.7677012609,
"f":0.790808043
},
"nmod:tmod":{
"p":0.7291941876,
"r":0.7510204082,
"f":0.7399463807
},
"nummod":{
"p":0.8324715615,
"r":0.5363091272,
"f":0.652350081
},
"mark:clf":{
"p":0.923958962,
"r":0.5710555763,
"f":0.7058552328
},
"auxpass":{
"p":0.8864864865,
"r":0.8864864865,
"f":0.8864864865
},
"nsubj":{
"p":0.7838943894,
"r":0.7293944233,
"f":0.7556630186
},
"acl":{
"p":0.7085714286,
"r":0.5501941209,
"f":0.6194192944
},
"advmod":{
"p":0.8221938776,
"r":0.7306733167,
"f":0.7737366463
},
"mark":{
"p":0.7447306792,
"r":0.6967572305,
"f":0.7199456645
},
"xcomp":{
"p":0.7822878229,
"r":0.6905537459,
"f":0.7335640138
},
"nmod:assmod":{
"p":0.7571008815,
"r":0.7217553688,
"f":0.7390057361
},
"det":{
"p":0.8367670365,
"r":0.618629174,
"f":0.7113506231
},
"amod":{
"p":0.7567811935,
"r":0.6575019639,
"f":0.7036569987
},
"nmod:prep":{
"p":0.6989096025,
"r":0.6010284332,
"f":0.6462839486
},
"root":{
"p":0.7426623746,
"r":0.6529049442,
"f":0.694897236
},
"aux:prtmod":{
"p":0.9058823529,
"r":0.825,
"f":0.8635514019
},
"compound:nn":{
"p":0.7339595888,
"r":0.700676819,
"f":0.716932133
},
"dobj":{
"p":0.802248996,
"r":0.7397422604,
"f":0.76972873
},
"ccomp":{
"p":0.6483430799,
"r":0.6465785381,
"f":0.6474596068
},
"advmod:rcomp":{
"p":0.8196202532,
"r":0.7174515235,
"f":0.765140325
},
"nmod:topic":{
"p":0.3596059113,
"r":0.237012987,
"f":0.2857142857
},
"cop":{
"p":0.7555739059,
"r":0.5888030888,
"f":0.6618444846
},
"discourse":{
"p":0.5577797998,
"r":0.5057755776,
"f":0.5305062743
},
"neg":{
"p":0.8365527489,
"r":0.6694411415,
"f":0.7437252312
},
"aux:modal":{
"p":0.8626198083,
"r":0.8376421923,
"f":0.8499475341
},
"nmod":{
"p":0.7152,
"r":0.6065128901,
"f":0.6563876652
},
"aux:ba":{
"p":0.8444444444,
"r":0.8085106383,
"f":0.8260869565
},
"advmod:loc":{
"p":0.6130268199,
"r":0.4747774481,
"f":0.5351170569
},
"aux:asp":{
"p":0.9095435685,
"r":0.8740031898,
"f":0.8914192761
},
"conj":{
"p":0.5032329577,
"r":0.5149338374,
"f":0.5090161637
},
"nsubjpass":{
"p":0.8292682927,
"r":0.68,
"f":0.7472527473
},
"compound:vc":{
"p":0.4486486486,
"r":0.4300518135,
"f":0.4391534392
},
"advcl:loc":{
"p":0.5945945946,
"r":0.4714285714,
"f":0.5258964143
},
"cc":{
"p":0.7013108614,
"r":0.6645962733,
"f":0.6824601367
},
"advmod:dvp":{
"p":0.8045112782,
"r":0.6645962733,
"f":0.7278911565
},
"appos":{
"p":0.8658536585,
"r":0.816091954,
"f":0.8402366864
},
"name":{
"p":0.5625,
"r":0.4666666667,
"f":0.5101214575
},
"parataxis:prnmod":{
"p":0.5,
"r":0.1278195489,
"f":0.2035928144
},
"nmod:poss":{
"p":0.6352941176,
"r":0.4,
"f":0.4909090909
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.7346153846,
"r":0.6409395973,
"f":0.6845878136
},
"amod:ordmod":{
"p":0.6181818182,
"r":0.53125,
"f":0.5714285714
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.9268292683,
"r":0.9047619048,
"f":0.9156626506
}
},
"ents_per_type":{
"DATE":{
"p":0.758780037,
"r":0.8136769078,
"f":0.7852702056
},
"GPE":{
"p":0.7517889088,
"r":0.8216031281,
"f":0.7851471275
},
"ORDINAL":{
"p":0.8720930233,
"r":0.7894736842,
"f":0.8287292818
},
"FAC":{
"p":0.5076923077,
"r":0.3548387097,
"f":0.417721519
},
"PERSON":{
"p":0.7917511832,
"r":0.7545103093,
"f":0.7726822831
},
"ORG":{
"p":0.6896831844,
"r":0.6461187215,
"f":0.6671905697
},
"QUANTITY":{
"p":0.7706422018,
"r":0.6222222222,
"f":0.6885245902
},
"CARDINAL":{
"p":0.6181818182,
"r":0.5141129032,
"f":0.5613648872
},
"LOC":{
"p":0.5247148289,
"r":0.3709677419,
"f":0.4346456693
},
"TIME":{
"p":0.7209302326,
"r":0.7524271845,
"f":0.7363420428
},
"NORP":{
"p":0.6646153846,
"r":0.4537815126,
"f":0.5393258427
},
"WORK_OF_ART":{
"p":0.5733333333,
"r":0.2866666667,
"f":0.3822222222
},
"PRODUCT":{
"p":0.2,
"r":0.0612244898,
"f":0.09375
},
"MONEY":{
"p":0.9230769231,
"r":0.8,
"f":0.8571428571
},
"PERCENT":{
"p":0.7613636364,
"r":0.8072289157,
"f":0.783625731
},
"EVENT":{
"p":0.5688073394,
"r":0.4558823529,
"f":0.506122449
},
"LAW":{
"p":0.4814814815,
"r":0.2166666667,
"f":0.2988505747
},
"LANGUAGE":{
"p":0.6363636364,
"r":0.7777777778,
"f":0.7
}
}
},
"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"
]
}