zh_core_web_lg / meta.json
osanseviero's picture
Update spaCy pipeline
7dfbadd
raw
history blame
10 kB
{
"lang":"zh",
"name":"core_web_lg",
"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":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"
],
"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":0.9037457747,
"dep_uas":0.7069146954,
"dep_las":0.6555390607,
"ents_p":0.7358998362,
"ents_r":0.6910989011,
"ents_f":0.7127961011,
"sents_p":0.7896445968,
"sents_r":0.7286499084,
"sents_f":0.7579220779,
"speed":9733.8076235494,
"dep_las_per_type":{
"dep":{
"p":0.4876810512,
"r":0.3299989896,
"f":0.3936362541
},
"case":{
"p":0.8168795974,
"r":0.7674587779,
"f":0.7913983872
},
"nmod:tmod":{
"p":0.7313237221,
"r":0.7591836735,
"f":0.7449933244
},
"nummod":{
"p":0.8191268191,
"r":0.5249833444,
"f":0.6398700771
},
"mark:clf":{
"p":0.9383017715,
"r":0.572920552,
"f":0.7114404817
},
"auxpass":{
"p":0.8817204301,
"r":0.8864864865,
"f":0.884097035
},
"nsubj":{
"p":0.7777050039,
"r":0.7292715883,
"f":0.7527099842
},
"acl":{
"p":0.7153127247,
"r":0.5518580144,
"f":0.623043206
},
"advmod":{
"p":0.8195641156,
"r":0.7331670823,
"f":0.7739619481
},
"mark":{
"p":0.7456996746,
"r":0.7028921998,
"f":0.7236634333
},
"xcomp":{
"p":0.7944444444,
"r":0.6986970684,
"f":0.7435008666
},
"nmod:assmod":{
"p":0.7745130406,
"r":0.7301587302,
"f":0.7516821532
},
"det":{
"p":0.8369132856,
"r":0.6162858817,
"f":0.709851552
},
"amod":{
"p":0.7794589638,
"r":0.6677140613,
"f":0.7192722657
},
"nmod:prep":{
"p":0.7016613644,
"r":0.6004234725,
"f":0.6471067645
},
"root":{
"p":0.7394862036,
"r":0.6469119361,
"f":0.6901083289
},
"aux:prtmod":{
"p":0.9246031746,
"r":0.8321428571,
"f":0.8759398496
},
"compound:nn":{
"p":0.7463895738,
"r":0.7170896785,
"f":0.7314463238
},
"dobj":{
"p":0.7939269334,
"r":0.7435935417,
"f":0.7679363622
},
"ccomp":{
"p":0.6330907698,
"r":0.6426905132,
"f":0.6378545244
},
"advmod:rcomp":{
"p":0.8229813665,
"r":0.7340720222,
"f":0.775988287
},
"nmod:topic":{
"p":0.3762886598,
"r":0.237012987,
"f":0.2908366534
},
"cop":{
"p":0.7518367347,
"r":0.5926640927,
"f":0.6628283555
},
"discourse":{
"p":0.5575139147,
"r":0.4958745875,
"f":0.5248908297
},
"neg":{
"p":0.8395802099,
"r":0.6658739596,
"f":0.7427055703
},
"aux:modal":{
"p":0.8475289169,
"r":0.8335056877,
"f":0.8404588113
},
"nmod":{
"p":0.7278688525,
"r":0.6024423338,
"f":0.6592427617
},
"aux:ba":{
"p":0.807486631,
"r":0.8031914894,
"f":0.8053333333
},
"advmod:loc":{
"p":0.6349206349,
"r":0.4747774481,
"f":0.5432937182
},
"aux:asp":{
"p":0.9013854931,
"r":0.8819776715,
"f":0.8915759774
},
"conj":{
"p":0.4869204402,
"r":0.5102079395,
"f":0.4982922551
},
"nsubjpass":{
"p":0.8048780488,
"r":0.66,
"f":0.7252747253
},
"compound:vc":{
"p":0.4647058824,
"r":0.4093264249,
"f":0.435261708
},
"advcl:loc":{
"p":0.5573770492,
"r":0.4857142857,
"f":0.5190839695
},
"cc":{
"p":0.7340425532,
"r":0.6734693878,
"f":0.7024525683
},
"advmod:dvp":{
"p":0.8320610687,
"r":0.6770186335,
"f":0.7465753425
},
"appos":{
"p":0.8740920097,
"r":0.8298850575,
"f":0.8514150943
},
"nmod:poss":{
"p":0.7341772152,
"r":0.4296296296,
"f":0.5420560748
},
"name":{
"p":0.6018518519,
"r":0.4814814815,
"f":0.5349794239
},
"nsubj:xsubj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"nmod:range":{
"p":0.7035714286,
"r":0.6610738255,
"f":0.6816608997
},
"parataxis:prnmod":{
"p":0.5454545455,
"r":0.1353383459,
"f":0.2168674699
},
"amod:ordmod":{
"p":0.564516129,
"r":0.546875,
"f":0.5555555556
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.9069767442,
"r":0.9285714286,
"f":0.9176470588
}
},
"ents_per_type":{
"DATE":{
"p":0.7675925926,
"r":0.82160555,
"f":0.7936811872
},
"GPE":{
"p":0.7719060524,
"r":0.8352883675,
"f":0.8023474178
},
"ORDINAL":{
"p":0.8388888889,
"r":0.7947368421,
"f":0.8162162162
},
"FAC":{
"p":0.5581395349,
"r":0.3870967742,
"f":0.4571428571
},
"ORG":{
"p":0.7028571429,
"r":0.6552511416,
"f":0.6782197716
},
"LOC":{
"p":0.5894039735,
"r":0.4784946237,
"f":0.528189911
},
"QUANTITY":{
"p":0.7889908257,
"r":0.637037037,
"f":0.7049180328
},
"WORK_OF_ART":{
"p":0.5,
"r":0.2866666667,
"f":0.3644067797
},
"CARDINAL":{
"p":0.614744352,
"r":0.5211693548,
"f":0.5641025641
},
"NORP":{
"p":0.6755952381,
"r":0.4768907563,
"f":0.5591133005
},
"TIME":{
"p":0.7365853659,
"r":0.7330097087,
"f":0.7347931873
},
"MONEY":{
"p":0.9322033898,
"r":0.8148148148,
"f":0.8695652174
},
"EVENT":{
"p":0.5681818182,
"r":0.3676470588,
"f":0.4464285714
},
"PERSON":{
"p":0.8077682686,
"r":0.7905927835,
"f":0.7990882449
},
"PERCENT":{
"p":0.7882352941,
"r":0.8072289157,
"f":0.7976190476
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.3333333333,
"r":0.1,
"f":0.1538461538
},
"LANGUAGE":{
"p":0.5555555556,
"r":0.5555555556,
"f":0.5555555556
}
}
},
"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"
]
}