zh_core_web_trf / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
c4017fc
raw history blame
No virus
9.97 kB
{
"lang":"zh",
"name":"core_web_trf",
"version":"3.1.0",
"description":"Chinese transformer pipeline (bert-base-chinese). Components: transformer, tagger, parser, 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":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"transformer":[
],
"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":[
"transformer",
"tagger",
"parser",
"attribute_ruler",
"ner"
],
"components":[
"transformer",
"tagger",
"parser",
"attribute_ruler",
"ner"
],
"disabled":[
],
"performance":{
"token_acc":0.9788303388,
"tag_acc":0.92444533,
"dep_uas":0.7661671924,
"dep_las":0.727981345,
"ents_p":0.6744976507,
"ents_r":0.7414285714,
"ents_f":0.7063811967,
"sents_p":0.6917940608,
"sents_r":0.655402031,
"sents_f":0.6731065139,
"speed":4304.7686585922,
"dep_las_per_type":{
"dep":{
"p":0.5611908839,
"r":0.4304334647,
"f":0.4871912168
},
"case":{
"p":0.9069435432,
"r":0.8472356935,
"f":0.8760734658
},
"nmod:tmod":{
"p":0.8046448087,
"r":0.8013605442,
"f":0.8029993183
},
"nummod":{
"p":0.9012345679,
"r":0.583610926,
"f":0.7084512738
},
"mark:clf":{
"p":0.9517326733,
"r":0.5736665423,
"f":0.7158482662
},
"auxpass":{
"p":0.9293478261,
"r":0.9243243243,
"f":0.9268292683
},
"nsubj":{
"p":0.8733342307,
"r":0.7969536912,
"f":0.8333975594
},
"acl":{
"p":0.8216805645,
"r":0.7104825291,
"f":0.762046401
},
"advmod":{
"p":0.8829383266,
"r":0.7643391521,
"f":0.819369342
},
"mark":{
"p":0.865225391,
"r":0.82427695,
"f":0.8442549372
},
"xcomp":{
"p":0.8221343874,
"r":0.67752443,
"f":0.7428571429
},
"nmod:assmod":{
"p":0.8709787817,
"r":0.7920946156,
"f":0.8296658517
},
"det":{
"p":0.9033306255,
"r":0.6514352665,
"f":0.7569775357
},
"amod":{
"p":0.8509749304,
"r":0.7199528672,
"f":0.78
},
"nmod:prep":{
"p":0.8192449048,
"r":0.7416817907,
"f":0.7785362756
},
"root":{
"p":0.7726093403,
"r":0.6940236391,
"f":0.7312110848
},
"aux:prtmod":{
"p":0.9042145594,
"r":0.8428571429,
"f":0.8724584104
},
"compound:nn":{
"p":0.8040945994,
"r":0.7708967851,
"f":0.7871458189
},
"dobj":{
"p":0.9081300813,
"r":0.8272848467,
"f":0.8658243547
},
"ccomp":{
"p":0.7877000842,
"r":0.7270606532,
"f":0.7561665993
},
"advmod:rcomp":{
"p":0.8475609756,
"r":0.7700831025,
"f":0.8069666183
},
"nmod:topic":{
"p":0.5434782609,
"r":0.487012987,
"f":0.5136986301
},
"cop":{
"p":0.8351555929,
"r":0.638996139,
"f":0.7240247904
},
"discourse":{
"p":0.6153846154,
"r":0.5478547855,
"f":0.5796595373
},
"neg":{
"p":0.8932496075,
"r":0.6765755054,
"f":0.7699594046
},
"aux:modal":{
"p":0.9019823789,
"r":0.8469493278,
"f":0.8736
},
"nmod":{
"p":0.7988505747,
"r":0.7544097693,
"f":0.7759944173
},
"aux:ba":{
"p":0.9265536723,
"r":0.8723404255,
"f":0.898630137
},
"advmod:loc":{
"p":0.80859375,
"r":0.6142433234,
"f":0.6981450253
},
"aux:asp":{
"p":0.9320882852,
"r":0.8755980861,
"f":0.9029605263
},
"conj":{
"p":0.6313854489,
"r":0.6168241966,
"f":0.6240198891
},
"nsubjpass":{
"p":0.8913043478,
"r":0.82,
"f":0.8541666667
},
"compound:vc":{
"p":0.5459183673,
"r":0.5544041451,
"f":0.5501285347
},
"advcl:loc":{
"p":0.7586206897,
"r":0.6285714286,
"f":0.6875
},
"cc":{
"p":0.7972477064,
"r":0.7710736469,
"f":0.7839422643
},
"advmod:dvp":{
"p":0.9076923077,
"r":0.7329192547,
"f":0.8109965636
},
"amod:ordmod":{
"p":0.6666666667,
"r":0.59375,
"f":0.6280991736
},
"appos":{
"p":0.9434889435,
"r":0.8827586207,
"f":0.9121140143
},
"nmod:poss":{
"p":0.7647058824,
"r":0.6740740741,
"f":0.7165354331
},
"name":{
"p":0.6097560976,
"r":0.5555555556,
"f":0.5813953488
},
"nsubj:xsubj":{
"p":0.5,
"r":0.1,
"f":0.1666666667
},
"nmod:range":{
"p":0.8295454545,
"r":0.7348993289,
"f":0.7793594306
},
"parataxis:prnmod":{
"p":0.3663366337,
"r":0.2781954887,
"f":0.3162393162
},
"erased":{
"p":0.0,
"r":0.0,
"f":0.0
},
"etc":{
"p":0.9285714286,
"r":0.9285714286,
"f":0.9285714286
}
},
"ents_per_type":{
"DATE":{
"p":0.6931530008,
"r":0.8126858276,
"f":0.7481751825
},
"GPE":{
"p":0.792633015,
"r":0.8519061584,
"f":0.8212014134
},
"CARDINAL":{
"p":0.5527502254,
"r":0.6179435484,
"f":0.5835316516
},
"ORDINAL":{
"p":0.8287292818,
"r":0.7894736842,
"f":0.8086253369
},
"FAC":{
"p":0.5301204819,
"r":0.4731182796,
"f":0.5
},
"ORG":{
"p":0.7304479879,
"r":0.7321156773,
"f":0.7312808818
},
"LOC":{
"p":0.1899383984,
"r":0.497311828,
"f":0.2748885587
},
"NORP":{
"p":0.6797900262,
"r":0.5441176471,
"f":0.6044340723
},
"QUANTITY":{
"p":0.7363636364,
"r":0.6,
"f":0.6612244898
},
"PERSON":{
"p":0.8649842271,
"r":0.8833762887,
"f":0.8740835193
},
"TIME":{
"p":0.711627907,
"r":0.7427184466,
"f":0.7268408551
},
"WORK_OF_ART":{
"p":0.1849315068,
"r":0.18,
"f":0.1824324324
},
"MONEY":{
"p":0.8682170543,
"r":0.8296296296,
"f":0.8484848485
},
"EVENT":{
"p":0.5804195804,
"r":0.6102941176,
"f":0.5949820789
},
"PERCENT":{
"p":0.7640449438,
"r":0.8192771084,
"f":0.7906976744
},
"PRODUCT":{
"p":0.5384615385,
"r":0.1428571429,
"f":0.2258064516
},
"LAW":{
"p":0.3076923077,
"r":0.2666666667,
"f":0.2857142857
},
"LANGUAGE":{
"p":0.8181818182,
"r":1.0,
"f":0.9
}
}
},
"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":"bert-base-chinese",
"author":"Hugging Face",
"url":"https://huggingface.co/bert-base-chinese",
"license":""
}
],
"requirements":[
"spacy-transformers>=1.0.3,<1.1.0",
"spacy-pkuseg>=0.0.27,<0.1.0"
]
}