en_core_web_trf / meta.json
adrianeboyd's picture
Update spaCy pipeline
11764b8
raw
history blame
10.4 kB
{
"lang":"en",
"name":"core_web_trf",
"version":"3.4.1",
"description":"English transformer pipeline (roberta-base). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.4.1,<3.5.0",
"spacy_git_version":"Unknown",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"transformer":[
],
"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"
],
"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":[
"transformer",
"tagger",
"parser",
"attribute_ruler",
"lemmatizer",
"ner"
],
"components":[
"transformer",
"tagger",
"parser",
"attribute_ruler",
"lemmatizer",
"ner"
],
"disabled":[
],
"performance":{
"token_acc":0.9993092439,
"token_p":0.9956819193,
"token_r":0.9957659295,
"token_f":0.9957239226,
"tag_acc":0.9780884117,
"sents_p":0.9586362315,
"sents_r":0.8699122633,
"sents_f":0.9121217361,
"dep_uas":0.9532621063,
"dep_las":0.9398782759,
"dep_las_per_type":{
"prep":{
"p":0.9227600801,
"r":0.9265414532,
"f":0.9246469007
},
"det":{
"p":0.9898458527,
"r":0.9896844165,
"f":0.989765128
},
"pobj":{
"p":0.9832568717,
"r":0.9847241312,
"f":0.9839899545
},
"nsubj":{
"p":0.9798134606,
"r":0.9803285871,
"f":0.9800709562
},
"aux":{
"p":0.9896677652,
"r":0.9891391436,
"f":0.9894033838
},
"advmod":{
"p":0.8973109244,
"r":0.8983678277,
"f":0.897839065
},
"relcl":{
"p":0.8737623762,
"r":0.8965892598,
"f":0.8850286533
},
"root":{
"p":0.9681547186,
"r":0.8784220595,
"f":0.921108152
},
"xcomp":{
"p":0.9436212505,
"r":0.9371859296,
"f":0.9403925806
},
"amod":{
"p":0.9436409624,
"r":0.9426627794,
"f":0.9431516173
},
"compound":{
"p":0.9528043393,
"r":0.9489307195,
"f":0.9508635844
},
"poss":{
"p":0.9863426391,
"r":0.98852657,
"f":0.987433397
},
"ccomp":{
"p":0.8568164509,
"r":0.916496945,
"f":0.8856524306
},
"attr":{
"p":0.9539036545,
"r":0.9659377628,
"f":0.9598829921
},
"case":{
"p":0.9885742673,
"r":0.995995996,
"f":0.9922712541
},
"mark":{
"p":0.9500131544,
"r":0.9568097509,
"f":0.9533993399
},
"intj":{
"p":0.6179976162,
"r":0.7597069597,
"f":0.6815642458
},
"advcl":{
"p":0.8078893443,
"r":0.7942583732,
"f":0.801015873
},
"cc":{
"p":0.8980490126,
"r":0.9028824303,
"f":0.9004592354
},
"neg":{
"p":0.9594594595,
"r":0.9618665329,
"f":0.9606614883
},
"conj":{
"p":0.8712276061,
"r":0.9121349446,
"f":0.8912121026
},
"nsubjpass":{
"p":0.9558748076,
"r":0.9553846154,
"f":0.9556296486
},
"auxpass":{
"p":0.9683257919,
"r":0.9749430524,
"f":0.9716231555
},
"dobj":{
"p":0.9751418751,
"r":0.972189019,
"f":0.9736632083
},
"nummod":{
"p":0.9544876684,
"r":0.947979798,
"f":0.9512226023
},
"npadvmod":{
"p":0.8592321755,
"r":0.8348134991,
"f":0.8468468468
},
"prt":{
"p":0.8991071429,
"r":0.9023297491,
"f":0.9007155635
},
"pcomp":{
"p":0.9302816901,
"r":0.925070028,
"f":0.9276685393
},
"expl":{
"p":0.9914529915,
"r":0.9935760171,
"f":0.992513369
},
"acl":{
"p":0.8488499452,
"r":0.8456082924,
"f":0.847226018
},
"agent":{
"p":0.9576719577,
"r":0.9731182796,
"f":0.9653333333
},
"dative":{
"p":0.835214447,
"r":0.8486238532,
"f":0.8418657565
},
"acomp":{
"p":0.94,
"r":0.9378684807,
"f":0.9389330306
},
"dep":{
"p":0.4232081911,
"r":0.4025974026,
"f":0.4126455907
},
"csubj":{
"p":0.8636363636,
"r":0.899408284,
"f":0.8811594203
},
"quantmod":{
"p":0.8827004219,
"r":0.8497156783,
"f":0.8658940397
},
"nmod":{
"p":0.8265657261,
"r":0.7318708105,
"f":0.7763413058
},
"appos":{
"p":0.8265618174,
"r":0.820824295,
"f":0.8236830649
},
"predet":{
"p":0.8548387097,
"r":0.9098712446,
"f":0.8814968815
},
"preconj":{
"p":0.6703296703,
"r":0.7093023256,
"f":0.6892655367
},
"oprd":{
"p":0.9015873016,
"r":0.847761194,
"f":0.8738461538
},
"parataxis":{
"p":0.6003752345,
"r":0.694143167,
"f":0.6438631791
},
"meta":{
"p":0.2156862745,
"r":0.6346153846,
"f":0.3219512195
},
"csubjpass":{
"p":0.7142857143,
"r":0.8333333333,
"f":0.7692307692
}
},
"ents_p":0.8953563447,
"ents_r":0.9028445513,
"ents_f":0.8990848565,
"ents_per_type":{
"DATE":{
"p":0.8842563783,
"r":0.9022222222,
"f":0.8931489629
},
"GPE":{
"p":0.9562166713,
"r":0.950348675,
"f":0.953273643
},
"ORDINAL":{
"p":0.8053892216,
"r":0.8354037267,
"f":0.8201219512
},
"ORG":{
"p":0.8987006099,
"r":0.8984623542,
"f":0.8985814663
},
"FAC":{
"p":0.5353535354,
"r":0.8153846154,
"f":0.6463414634
},
"QUANTITY":{
"p":0.7120418848,
"r":0.7472527473,
"f":0.7292225201
},
"LOC":{
"p":0.8248407643,
"r":0.8248407643,
"f":0.8248407643
},
"CARDINAL":{
"p":0.8490241102,
"r":0.8793103448,
"f":0.8639018692
},
"PERSON":{
"p":0.9408020369,
"r":0.9647519582,
"f":0.9526264905
},
"NORP":{
"p":0.9305666401,
"r":0.9328,
"f":0.9316819816
},
"LAW":{
"p":0.625,
"r":0.703125,
"f":0.6617647059
},
"PRODUCT":{
"p":0.6823529412,
"r":0.5497630332,
"f":0.6089238845
},
"TIME":{
"p":0.7527472527,
"r":0.8011695906,
"f":0.776203966
},
"EVENT":{
"p":0.7883211679,
"r":0.6206896552,
"f":0.6945337621
},
"WORK_OF_ART":{
"p":0.6077348066,
"r":0.5670103093,
"f":0.5866666667
},
"MONEY":{
"p":0.9120481928,
"r":0.893742621,
"f":0.9028026237
},
"PERCENT":{
"p":0.9225908373,
"r":0.8943338438,
"f":0.9082426128
},
"LANGUAGE":{
"p":0.9615384615,
"r":0.78125,
"f":0.8620689655
}
},
"speed":6118.8721996645
},
"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":"roberta-base",
"author":"Yinhan Liu and Myle Ott and Naman Goyal and Jingfei Du and Mandar Joshi and Danqi Chen and Omer Levy and Mike Lewis and Luke Zettlemoyer and Veselin Stoyanov",
"url":"https://github.com/pytorch/fairseq/tree/master/examples/roberta",
"license":""
}
],
"requirements":[
"spacy-transformers>=1.1.2,<1.2.0"
]
}