en_core_web_trf / meta.json
Adriane Boyd
Update spaCy pipeline
607d57e
raw
history blame
10.5 kB
{
"lang":"en",
"name":"core_web_trf",
"version":"3.4.0",
"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":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"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":0.9781415701,
"sents_p":0.9530354255,
"sents_r":0.8553994327,
"sents_f":0.9015817834,
"dep_uas":0.9519734881,
"dep_las":0.9386831877,
"dep_las_per_type":{
"prep":{
"p":0.9231585329,
"r":0.9244545627,
"f":0.9238060932
},
"det":{
"p":0.990168482,
"r":0.9896436435,
"f":0.9899059932
},
"pobj":{
"p":0.9838152106,
"r":0.9834675044,
"f":0.9836413268
},
"nsubj":{
"p":0.9802349023,
"r":0.9799342826,
"f":0.9800845694
},
"aux":{
"p":0.989841383,
"r":0.9888720734,
"f":0.9893564908
},
"advmod":{
"p":0.89568951,
"r":0.8950866566,
"f":0.8953879818
},
"relcl":{
"p":0.8737588652,
"r":0.8940493469,
"f":0.8837876614
},
"root":{
"p":0.9671492614,
"r":0.8681311432,
"f":0.9149690607
},
"xcomp":{
"p":0.9440836941,
"r":0.9393395549,
"f":0.9417056495
},
"amod":{
"p":0.942079689,
"r":0.942079689,
"f":0.942079689
},
"compound":{
"p":0.9517283813,
"r":0.947594119,
"f":0.9496567506
},
"poss":{
"p":0.9867496487,
"r":0.989331723,
"f":0.9880389989
},
"ccomp":{
"p":0.8520136778,
"r":0.9134419552,
"f":0.8816591311
},
"attr":{
"p":0.9524400331,
"r":0.9684608915,
"f":0.960383653
},
"case":{
"p":0.9880774963,
"r":0.9954954955,
"f":0.9917726253
},
"mark":{
"p":0.9498292619,
"r":0.9581346052,
"f":0.953963857
},
"intj":{
"p":0.6186839013,
"r":0.7714285714,
"f":0.686664493
},
"advcl":{
"p":0.8043588444,
"r":0.7992948879,
"f":0.8018188708
},
"cc":{
"p":0.8945117605,
"r":0.9006099749,
"f":0.8975505096
},
"neg":{
"p":0.9619429144,
"r":0.9638735575,
"f":0.9629072682
},
"conj":{
"p":0.8646652371,
"r":0.9136455186,
"f":0.8884808422
},
"nsubjpass":{
"p":0.9548949257,
"r":0.9553846154,
"f":0.9551397078
},
"auxpass":{
"p":0.9660479855,
"r":0.9722095672,
"f":0.9691189827
},
"dobj":{
"p":0.9735014766,
"r":0.9719499562,
"f":0.9727250977
},
"nummod":{
"p":0.9542450432,
"r":0.947979798,
"f":0.9511021029
},
"npadvmod":{
"p":0.8555147059,
"r":0.826642984,
"f":0.840831075
},
"prt":{
"p":0.8947368421,
"r":0.9139784946,
"f":0.9042553191
},
"pcomp":{
"p":0.929676512,
"r":0.9257703081,
"f":0.9277192982
},
"expl":{
"p":0.9914529915,
"r":0.9935760171,
"f":0.992513369
},
"acl":{
"p":0.8457765668,
"r":0.8466993999,
"f":0.8462377317
},
"agent":{
"p":0.9542253521,
"r":0.9713261649,
"f":0.9626998224
},
"dative":{
"p":0.8430493274,
"r":0.8623853211,
"f":0.8526077098
},
"acomp":{
"p":0.9473443223,
"r":0.9383219955,
"f":0.9428115744
},
"dep":{
"p":0.4019448947,
"r":0.4025974026,
"f":0.402270884
},
"csubj":{
"p":0.8928571429,
"r":0.8875739645,
"f":0.8902077151
},
"quantmod":{
"p":0.880334728,
"r":0.8545897644,
"f":0.8672712284
},
"nmod":{
"p":0.8183701657,
"r":0.7221206581,
"f":0.7672385885
},
"appos":{
"p":0.8213058419,
"r":0.8295010846,
"f":0.8253831211
},
"predet":{
"p":0.8542510121,
"r":0.9055793991,
"f":0.8791666667
},
"preconj":{
"p":0.6276595745,
"r":0.6860465116,
"f":0.6555555556
},
"oprd":{
"p":0.9056603774,
"r":0.8597014925,
"f":0.8820826953
},
"parataxis":{
"p":0.5711645102,
"r":0.6702819957,
"f":0.6167664671
},
"meta":{
"p":0.1927710843,
"r":0.6153846154,
"f":0.2935779817
},
"csubjpass":{
"p":0.7142857143,
"r":0.8333333333,
"f":0.7692307692
}
},
"ents_p":0.9017005601,
"ents_r":0.8948818109,
"ents_f":0.8982782456,
"ents_per_type":{
"DATE":{
"p":0.8982188295,
"r":0.8965079365,
"f":0.8973625675
},
"GPE":{
"p":0.95865194,
"r":0.9442119944,
"f":0.9513771782
},
"ORDINAL":{
"p":0.8161993769,
"r":0.8136645963,
"f":0.8149300156
},
"ORG":{
"p":0.9070641955,
"r":0.895281018,
"f":0.9011340894
},
"FAC":{
"p":0.5632183908,
"r":0.7538461538,
"f":0.6447368421
},
"QUANTITY":{
"p":0.7112299465,
"r":0.7307692308,
"f":0.7208672087
},
"LOC":{
"p":0.853820598,
"r":0.8184713376,
"f":0.8357723577
},
"CARDINAL":{
"p":0.862396204,
"r":0.8644470868,
"f":0.8634204276
},
"PERSON":{
"p":0.9394132653,
"r":0.9614882507,
"f":0.9503225806
},
"NORP":{
"p":0.9274778405,
"r":0.9208,
"f":0.9241268567
},
"MONEY":{
"p":0.9214975845,
"r":0.9008264463,
"f":0.9110447761
},
"TIME":{
"p":0.7471910112,
"r":0.7777777778,
"f":0.7621776504
},
"EVENT":{
"p":0.803030303,
"r":0.6091954023,
"f":0.6928104575
},
"PRODUCT":{
"p":0.6139240506,
"r":0.4597156398,
"f":0.5257452575
},
"WORK_OF_ART":{
"p":0.5885714286,
"r":0.5309278351,
"f":0.5582655827
},
"LAW":{
"p":0.6142857143,
"r":0.671875,
"f":0.6417910448
},
"PERCENT":{
"p":0.9222222222,
"r":0.8897396631,
"f":0.9056897896
},
"LANGUAGE":{
"p":0.9583333333,
"r":0.71875,
"f":0.8214285714
}
},
"speed":5935.3253234178
},
"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":"MIT"
}
],
"requirements":[
"spacy-transformers>=1.1.2,<1.2.0"
]
}