en_core_web_lg / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
9a8869b
raw history blame
No virus
10.4 kB
{
"lang":"en",
"name":"core_web_lg",
"version":"3.2.0",
"description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.2.0,<3.3.0",
"spacy_git_version":"bb26550e2",
"vectors":{
"width":300,
"vectors":684830,
"keys":684830,
"name":"en_vectors"
},
"labels":{
"tok2vec":[
],
"tagger":[
"$",
"''",
",",
"-LRB-",
"-RRB-",
".",
":",
"ADD",
"AFX",
"CC",
"CD",
"DT",
"EX",
"FW",
"HYPH",
"IN",
"JJ",
"JJR",
"JJS",
"LS",
"MD",
"NFP",
"NN",
"NNP",
"NNPS",
"NNS",
"PDT",
"POS",
"PRP",
"PRP$",
"RB",
"RBR",
"RBS",
"RP",
"SYM",
"TO",
"UH",
"VB",
"VBD",
"VBG",
"VBN",
"VBP",
"VBZ",
"WDT",
"WP",
"WP$",
"WRB",
"XX",
"``"
],
"parser":[
"ROOT",
"acl",
"acomp",
"advcl",
"advmod",
"agent",
"amod",
"appos",
"attr",
"aux",
"auxpass",
"case",
"cc",
"ccomp",
"compound",
"conj",
"csubj",
"csubjpass",
"dative",
"dep",
"det",
"dobj",
"expl",
"intj",
"mark",
"meta",
"neg",
"nmod",
"npadvmod",
"nsubj",
"nsubjpass",
"nummod",
"oprd",
"parataxis",
"pcomp",
"pobj",
"poss",
"preconj",
"predet",
"prep",
"prt",
"punct",
"quantmod",
"relcl",
"xcomp"
],
"senter":[
"I",
"S"
],
"attribute_ruler":[
],
"lemmatizer":[
],
"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",
"lemmatizer",
"ner"
],
"components":[
"tok2vec",
"tagger",
"parser",
"senter",
"attribute_ruler",
"lemmatizer",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9993053983,
"token_p":0.9956742163,
"token_r":0.9957505887,
"token_f":0.9957124011,
"tag_acc":0.9741780493,
"sents_p":0.9179358172,
"sents_r":0.8906260307,
"sents_f":0.9040747313,
"dep_uas":0.9200593914,
"dep_las":0.9021556352,
"dep_las_per_type":{
"prep":{
"p":0.8578239976,
"r":0.8669702144,
"f":0.8623728558
},
"det":{
"p":0.9798012706,
"r":0.9809997554,
"f":0.9804001467
},
"pobj":{
"p":0.9617211838,
"r":0.9698409582,
"f":0.9657640043
},
"nsubj":{
"p":0.9608471258,
"r":0.9461555312,
"f":0.9534447363
},
"aux":{
"p":0.9807231056,
"r":0.9828184813,
"f":0.9817696754
},
"advmod":{
"p":0.8600169779,
"r":0.8523472993,
"f":0.8561649624
},
"relcl":{
"p":0.755259467,
"r":0.7815674891,
"f":0.7681883024
},
"root":{
"p":0.9196325281,
"r":0.8914836071,
"f":0.905339318
},
"xcomp":{
"p":0.8886906885,
"r":0.8941134243,
"f":0.8913938093
},
"amod":{
"p":0.9216490817,
"r":0.9168124393,
"f":0.9192243983
},
"compound":{
"p":0.9188224309,
"r":0.9316662954,
"f":0.9251997898
},
"poss":{
"p":0.9760755931,
"r":0.9772544283,
"f":0.976664655
},
"ccomp":{
"p":0.7797340326,
"r":0.8478615071,
"f":0.8123719387
},
"attr":{
"p":0.8931845357,
"r":0.9423885618,
"f":0.9171270718
},
"case":{
"p":0.9782823297,
"r":0.991991992,
"f":0.9850894632
},
"mark":{
"p":0.9105669417,
"r":0.9064652888,
"f":0.9085114859
},
"intj":{
"p":0.6737089202,
"r":0.6307692308,
"f":0.6515323496
},
"advcl":{
"p":0.67003282,
"r":0.6683455049,
"f":0.6691880988
},
"cc":{
"p":0.8372232916,
"r":0.8323167085,
"f":0.8347627901
},
"neg":{
"p":0.9408548708,
"r":0.9498243853,
"f":0.9453183521
},
"conj":{
"p":0.7653624433,
"r":0.7854984894,
"f":0.7752997453
},
"nsubjpass":{
"p":0.9327377824,
"r":0.9102564103,
"f":0.9213599792
},
"auxpass":{
"p":0.9543624161,
"r":0.9717539863,
"f":0.962979684
},
"dobj":{
"p":0.9222826087,
"r":0.9466092916,
"f":0.9342876244
},
"nummod":{
"p":0.9430395913,
"r":0.9323232323,
"f":0.9376507937
},
"npadvmod":{
"p":0.7866254349,
"r":0.7229129663,
"f":0.7534246575
},
"prt":{
"p":0.8190082645,
"r":0.8879928315,
"f":0.8521066208
},
"pcomp":{
"p":0.879020979,
"r":0.8802521008,
"f":0.8796361092
},
"expl":{
"p":0.9809725159,
"r":0.9935760171,
"f":0.9872340426
},
"acl":{
"p":0.7443997702,
"r":0.7070376432,
"f":0.7252378288
},
"agent":{
"p":0.8928571429,
"r":0.9408602151,
"f":0.9162303665
},
"dative":{
"p":0.7729591837,
"r":0.6949541284,
"f":0.731884058
},
"acomp":{
"p":0.9102505695,
"r":0.906122449,
"f":0.9081818182
},
"dep":{
"p":0.4491525424,
"r":0.1720779221,
"f":0.2488262911
},
"csubj":{
"p":0.7243589744,
"r":0.6686390533,
"f":0.6953846154
},
"quantmod":{
"p":0.8686779059,
"r":0.7952883834,
"f":0.8303647159
},
"nmod":{
"p":0.76,
"r":0.5789152956,
"f":0.6572120374
},
"appos":{
"p":0.7035040431,
"r":0.6793926247,
"f":0.6912381373
},
"predet":{
"p":0.8300395257,
"r":0.9012875536,
"f":0.8641975309
},
"preconj":{
"p":0.5784313725,
"r":0.6860465116,
"f":0.6276595745
},
"oprd":{
"p":0.8379310345,
"r":0.7253731343,
"f":0.7776
},
"parataxis":{
"p":0.6312849162,
"r":0.4902386117,
"f":0.5518925519
},
"meta":{
"p":0.7647058824,
"r":0.25,
"f":0.3768115942
},
"csubjpass":{
"p":0.5555555556,
"r":0.8333333333,
"f":0.6666666667
}
},
"ents_p":0.8574246409,
"ents_r":0.8490084135,
"ents_f":0.8531957725,
"ents_per_type":{
"DATE":{
"p":0.8695102686,
"r":0.8736507937,
"f":0.8715756136
},
"GPE":{
"p":0.9231641622,
"r":0.9082287308,
"f":0.9156355456
},
"ORDINAL":{
"p":0.7971428571,
"r":0.8664596273,
"f":0.8303571429
},
"ORG":{
"p":0.8194444444,
"r":0.8290031813,
"f":0.8241960991
},
"QUANTITY":{
"p":0.7959183673,
"r":0.6428571429,
"f":0.7112462006
},
"CARDINAL":{
"p":0.8221709007,
"r":0.8466111772,
"f":0.834212068
},
"PERSON":{
"p":0.8823895457,
"r":0.9255874674,
"f":0.9034724435
},
"NORP":{
"p":0.9027888446,
"r":0.9064,
"f":0.9045908184
},
"LOC":{
"p":0.7185185185,
"r":0.6178343949,
"f":0.6643835616
},
"FAC":{
"p":0.4263565891,
"r":0.4230769231,
"f":0.4247104247
},
"TIME":{
"p":0.7396825397,
"r":0.6812865497,
"f":0.7092846271
},
"PRODUCT":{
"p":0.6022727273,
"r":0.2511848341,
"f":0.3545150502
},
"EVENT":{
"p":0.5882352941,
"r":0.2873563218,
"f":0.3861003861
},
"WORK_OF_ART":{
"p":0.4692307692,
"r":0.3144329897,
"f":0.3765432099
},
"LAW":{
"p":0.5272727273,
"r":0.453125,
"f":0.487394958
},
"MONEY":{
"p":0.8990498812,
"r":0.893742621,
"f":0.8963883955
},
"PERCENT":{
"p":0.9202551834,
"r":0.8836140888,
"f":0.9015625
},
"LANGUAGE":{
"p":0.8,
"r":0.625,
"f":0.701754386
}
},
"speed":7471.5995598921
},
"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":"ClearNLP Constituent-to-Dependency Conversion",
"url":"https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md",
"license":"Citation provided for reference, no code packaged with model",
"author":"Emory University"
},
{
"name":"WordNet 3.0",
"url":"https://wordnet.princeton.edu/",
"author":"Princeton University",
"license":"WordNet 3.0 License"
},
{
"name":"GloVe Common Crawl",
"url":"https://nlp.stanford.edu/projects/glove/",
"license":"Public Domain Dedication and License v1.0",
"author":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning"
}
],
"requirements":[
]
}