528 lines
No EOL
10 KiB
JSON
528 lines
No EOL
10 KiB
JSON
{
|
|
"lang":"en",
|
|
"name":"core_web_sm",
|
|
"version":"3.4.0",
|
|
"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":">=3.4.0,<3.5.0",
|
|
"spacy_git_version":"dd038b536",
|
|
"vectors":{
|
|
"width":0,
|
|
"vectors":0,
|
|
"keys":0,
|
|
"name":null,
|
|
"mode":"default"
|
|
},
|
|
"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",
|
|
"_SP",
|
|
"``"
|
|
],
|
|
"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"
|
|
],
|
|
"attribute_ruler":[
|
|
|
|
],
|
|
"lemmatizer":[
|
|
|
|
],
|
|
"ner":[
|
|
"CARDINAL",
|
|
"DATE",
|
|
"EVENT",
|
|
"FAC",
|
|
"GPE",
|
|
"LANGUAGE",
|
|
"LAW",
|
|
"LOC",
|
|
"MONEY",
|
|
"NORP",
|
|
"ORDINAL",
|
|
"ORG",
|
|
"PERCENT",
|
|
"PERSON",
|
|
"PRODUCT",
|
|
"QUANTITY",
|
|
"TIME",
|
|
"WORK_OF_ART",
|
|
"cdtr.bic",
|
|
"cdtr.iban",
|
|
"cdtr.name",
|
|
"invoice.date",
|
|
"invoice.number",
|
|
"invoice.total"
|
|
]
|
|
},
|
|
"pipeline":[
|
|
"tok2vec",
|
|
"attribute_ruler",
|
|
"lemmatizer",
|
|
"ner"
|
|
],
|
|
"components":[
|
|
"tok2vec",
|
|
"tagger",
|
|
"parser",
|
|
"senter",
|
|
"attribute_ruler",
|
|
"lemmatizer",
|
|
"ner"
|
|
],
|
|
"disabled":[
|
|
"tagger",
|
|
"parser",
|
|
"senter"
|
|
],
|
|
"performance":{
|
|
"token_acc":0.9993092439,
|
|
"token_p":0.9956819193,
|
|
"token_r":0.9957659295,
|
|
"token_f":0.9957239226,
|
|
"tag_acc":0.9726250474,
|
|
"sents_p":0.9191788296,
|
|
"sents_r":0.8890428129,
|
|
"sents_f":0.9038596962,
|
|
"dep_uas":0.9165718428,
|
|
"dep_las":0.8978441095,
|
|
"dep_las_per_type":{
|
|
"prep":{
|
|
"p":0.8546376267,
|
|
"r":0.8635553026,
|
|
"f":0.8590733226
|
|
},
|
|
"det":{
|
|
"p":0.9768701389,
|
|
"r":0.9781048683,
|
|
"f":0.9774871137
|
|
},
|
|
"pobj":{
|
|
"p":0.9605592002,
|
|
"r":0.9659532692,
|
|
"f":0.9632486833
|
|
},
|
|
"nsubj":{
|
|
"p":0.9545715675,
|
|
"r":0.9463745893,
|
|
"f":0.9504554055
|
|
},
|
|
"aux":{
|
|
"p":0.9798401421,
|
|
"r":0.9821953174,
|
|
"f":0.9810163162
|
|
},
|
|
"advmod":{
|
|
"p":0.8545653823,
|
|
"r":0.8527679623,
|
|
"f":0.8536657262
|
|
},
|
|
"relcl":{
|
|
"p":0.7656695157,
|
|
"r":0.7801161103,
|
|
"f":0.7728253055
|
|
},
|
|
"root":{
|
|
"p":0.91776518,
|
|
"r":0.8864041164,
|
|
"f":0.9018120805
|
|
},
|
|
"xcomp":{
|
|
"p":0.882290562,
|
|
"r":0.895908112,
|
|
"f":0.889047195
|
|
},
|
|
"amod":{
|
|
"p":0.9154102213,
|
|
"r":0.908649174,
|
|
"f":0.9120171674
|
|
},
|
|
"compound":{
|
|
"p":0.9121588361,
|
|
"r":0.9287703275,
|
|
"f":0.9203896355
|
|
},
|
|
"poss":{
|
|
"p":0.9735258724,
|
|
"r":0.9770531401,
|
|
"f":0.9752863171
|
|
},
|
|
"ccomp":{
|
|
"p":0.7657557167,
|
|
"r":0.8389002037,
|
|
"f":0.8006609
|
|
},
|
|
"attr":{
|
|
"p":0.9032126881,
|
|
"r":0.9339781329,
|
|
"f":0.9183378127
|
|
},
|
|
"case":{
|
|
"p":0.9773063641,
|
|
"r":0.9914914915,
|
|
"f":0.9843478261
|
|
},
|
|
"mark":{
|
|
"p":0.9002893975,
|
|
"r":0.9067302597,
|
|
"f":0.9034983498
|
|
},
|
|
"intj":{
|
|
"p":0.6514555468,
|
|
"r":0.6065934066,
|
|
"f":0.6282245827
|
|
},
|
|
"advcl":{
|
|
"p":0.6653050804,
|
|
"r":0.6562578696,
|
|
"f":0.6607505071
|
|
},
|
|
"cc":{
|
|
"p":0.8285611165,
|
|
"r":0.8237052984,
|
|
"f":0.8261260721
|
|
},
|
|
"neg":{
|
|
"p":0.9452191235,
|
|
"r":0.9523331661,
|
|
"f":0.9487628093
|
|
},
|
|
"conj":{
|
|
"p":0.7577601192,
|
|
"r":0.7682527694,
|
|
"f":0.7629703713
|
|
},
|
|
"nsubjpass":{
|
|
"p":0.9216589862,
|
|
"r":0.9230769231,
|
|
"f":0.9223674097
|
|
},
|
|
"auxpass":{
|
|
"p":0.946875,
|
|
"r":0.9662870159,
|
|
"f":0.9564825254
|
|
},
|
|
"dobj":{
|
|
"p":0.919205298,
|
|
"r":0.940154594,
|
|
"f":0.9295619288
|
|
},
|
|
"nummod":{
|
|
"p":0.9373886485,
|
|
"r":0.9300505051,
|
|
"f":0.9337051591
|
|
},
|
|
"npadvmod":{
|
|
"p":0.7748549323,
|
|
"r":0.7115452931,
|
|
"f":0.7418518519
|
|
},
|
|
"prt":{
|
|
"p":0.8097199341,
|
|
"r":0.8808243728,
|
|
"f":0.843776824
|
|
},
|
|
"pcomp":{
|
|
"p":0.8756183746,
|
|
"r":0.8676470588,
|
|
"f":0.8716144917
|
|
},
|
|
"expl":{
|
|
"p":0.9809322034,
|
|
"r":0.9914346895,
|
|
"f":0.9861554846
|
|
},
|
|
"acl":{
|
|
"p":0.7327887981,
|
|
"r":0.6852154937,
|
|
"f":0.7082041162
|
|
},
|
|
"agent":{
|
|
"p":0.8959044369,
|
|
"r":0.9408602151,
|
|
"f":0.9178321678
|
|
},
|
|
"dative":{
|
|
"p":0.7846153846,
|
|
"r":0.7018348624,
|
|
"f":0.7409200969
|
|
},
|
|
"acomp":{
|
|
"p":0.9127423823,
|
|
"r":0.8965986395,
|
|
"f":0.90459849
|
|
},
|
|
"dep":{
|
|
"p":0.3786764706,
|
|
"r":0.1672077922,
|
|
"f":0.231981982
|
|
},
|
|
"csubj":{
|
|
"p":0.7393939394,
|
|
"r":0.7218934911,
|
|
"f":0.7305389222
|
|
},
|
|
"quantmod":{
|
|
"p":0.8694493783,
|
|
"r":0.7952883834,
|
|
"f":0.8307170132
|
|
},
|
|
"nmod":{
|
|
"p":0.7147169811,
|
|
"r":0.577087142,
|
|
"f":0.6385704653
|
|
},
|
|
"appos":{
|
|
"p":0.7100509495,
|
|
"r":0.6650759219,
|
|
"f":0.686827957
|
|
},
|
|
"predet":{
|
|
"p":0.8636363636,
|
|
"r":0.8969957082,
|
|
"f":0.88
|
|
},
|
|
"preconj":{
|
|
"p":0.5769230769,
|
|
"r":0.6976744186,
|
|
"f":0.6315789474
|
|
},
|
|
"oprd":{
|
|
"p":0.8160535117,
|
|
"r":0.728358209,
|
|
"f":0.7697160883
|
|
},
|
|
"parataxis":{
|
|
"p":0.5835694051,
|
|
"r":0.4468546638,
|
|
"f":0.5061425061
|
|
},
|
|
"meta":{
|
|
"p":0.8666666667,
|
|
"r":0.5,
|
|
"f":0.6341463415
|
|
},
|
|
"csubjpass":{
|
|
"p":0.5,
|
|
"r":0.6666666667,
|
|
"f":0.5714285714
|
|
}
|
|
},
|
|
"ents_p":0.8565043157,
|
|
"ents_r":0.8348858173,
|
|
"ents_f":0.8455569081,
|
|
"ents_per_type":{
|
|
"DATE":{
|
|
"p":0.8804768041,
|
|
"r":0.8676190476,
|
|
"f":0.8740006396
|
|
},
|
|
"GPE":{
|
|
"p":0.9239884393,
|
|
"r":0.8917712692,
|
|
"f":0.9075940383
|
|
},
|
|
"ORDINAL":{
|
|
"p":0.7910447761,
|
|
"r":0.8229813665,
|
|
"f":0.8066971081
|
|
},
|
|
"ORG":{
|
|
"p":0.8107606679,
|
|
"r":0.8109756098,
|
|
"f":0.8108681246
|
|
},
|
|
"FAC":{
|
|
"p":0.3902439024,
|
|
"r":0.3692307692,
|
|
"f":0.3794466403
|
|
},
|
|
"CARDINAL":{
|
|
"p":0.8266978923,
|
|
"r":0.8394768133,
|
|
"f":0.8330383481
|
|
},
|
|
"PERSON":{
|
|
"p":0.8648820905,
|
|
"r":0.885770235,
|
|
"f":0.8752015479
|
|
},
|
|
"NORP":{
|
|
"p":0.9130787977,
|
|
"r":0.8992,
|
|
"f":0.9060862555
|
|
},
|
|
"TIME":{
|
|
"p":0.7492163009,
|
|
"r":0.6988304094,
|
|
"f":0.7231467474
|
|
},
|
|
"LOC":{
|
|
"p":0.7158273381,
|
|
"r":0.6337579618,
|
|
"f":0.6722972973
|
|
},
|
|
"QUANTITY":{
|
|
"p":0.7971014493,
|
|
"r":0.6043956044,
|
|
"f":0.6875
|
|
},
|
|
"EVENT":{
|
|
"p":0.6373626374,
|
|
"r":0.3333333333,
|
|
"f":0.4377358491
|
|
},
|
|
"WORK_OF_ART":{
|
|
"p":0.5230769231,
|
|
"r":0.3505154639,
|
|
"f":0.4197530864
|
|
},
|
|
"LAW":{
|
|
"p":0.6304347826,
|
|
"r":0.453125,
|
|
"f":0.5272727273
|
|
},
|
|
"MONEY":{
|
|
"p":0.9179548157,
|
|
"r":0.9114521842,
|
|
"f":0.9146919431
|
|
},
|
|
"PERCENT":{
|
|
"p":0.9171974522,
|
|
"r":0.8820826953,
|
|
"f":0.8992974239
|
|
},
|
|
"PRODUCT":{
|
|
"p":0.5,
|
|
"r":0.2274881517,
|
|
"f":0.3127035831
|
|
},
|
|
"LANGUAGE":{
|
|
"p":0.8,
|
|
"r":0.625,
|
|
"f":0.701754386
|
|
}
|
|
},
|
|
"speed":9012.0225085527
|
|
},
|
|
"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"
|
|
}
|
|
],
|
|
"requirements":[
|
|
|
|
]
|
|
} |