en_core_web_trf / meta.json
osanseviero's picture
Update spaCy pipeline
f96be1d
raw
history blame
10.3 kB
{
"lang":"en",
"name":"core_web_trf",
"version":"3.1.0",
"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":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"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":0.9993053983,
"tag_acc":0.9779597496,
"dep_uas":0.9529693229,
"dep_las":0.9394097615,
"ents_p":0.898632744,
"ents_r":0.8985877404,
"ents_f":0.8986102416,
"sents_p":0.9533882851,
"sents_r":0.8621940761,
"sents_f":0.9055009007,
"speed":5467.6411211076,
"dep_las_per_type":{
"prep":{
"p":0.9227131724,
"r":0.9254790362,
"f":0.9240940347
},
"det":{
"p":0.9901676798,
"r":0.9895620974,
"f":0.989864796
},
"pobj":{
"p":0.9827126617,
"r":0.9844492441,
"f":0.9835801864
},
"nsubj":{
"p":0.9797975371,
"r":0.9795399781,
"f":0.9796687407
},
"aux":{
"p":0.9890501202,
"r":0.9890501202,
"f":0.9890501202
},
"advmod":{
"p":0.8975934029,
"r":0.8974423692,
"f":0.8975178797
},
"relcl":{
"p":0.873105393,
"r":0.898766328,
"f":0.8857500447
},
"root":{
"p":0.9679445053,
"r":0.8744640148,
"f":0.9188327442
},
"xcomp":{
"p":0.940690151,
"r":0.9393395549,
"f":0.9400143678
},
"amod":{
"p":0.942555534,
"r":0.9429219307,
"f":0.9427386967
},
"compound":{
"p":0.952575817,
"r":0.9463689018,
"f":0.9494622154
},
"poss":{
"p":0.986746988,
"r":0.9891304348,
"f":0.9879372738
},
"ccomp":{
"p":0.8579088472,
"r":0.9124236253,
"f":0.8843268851
},
"attr":{
"p":0.9473251029,
"r":0.9680403701,
"f":0.9575707155
},
"case":{
"p":0.9880834161,
"r":0.995995996,
"f":0.9920239282
},
"mark":{
"p":0.9546054368,
"r":0.958399576,
"f":0.9564987439
},
"intj":{
"p":0.6154299176,
"r":0.7655677656,
"f":0.6823375775
},
"advcl":{
"p":0.8175954592,
"r":0.7980357593,
"f":0.8076972091
},
"cc":{
"p":0.8981217309,
"r":0.9036000478,
"f":0.9008525607
},
"neg":{
"p":0.957,
"r":0.9603612644,
"f":0.958677686
},
"conj":{
"p":0.8658565642,
"r":0.9149043303,
"f":0.8897049822
},
"nsubjpass":{
"p":0.958161157,
"r":0.9512820513,
"f":0.9547092126
},
"auxpass":{
"p":0.9672727273,
"r":0.969476082,
"f":0.9683731513
},
"dobj":{
"p":0.9737199457,
"r":0.9713921428,
"f":0.9725546513
},
"nummod":{
"p":0.9584077571,
"r":0.9484848485,
"f":0.9534204848
},
"npadvmod":{
"p":0.85505659,
"r":0.8319715808,
"f":0.8433561397
},
"prt":{
"p":0.8902546093,
"r":0.9086021505,
"f":0.8993348115
},
"pcomp":{
"p":0.9301833568,
"r":0.9236694678,
"f":0.9269149684
},
"expl":{
"p":0.9935897436,
"r":0.9957173448,
"f":0.9946524064
},
"acl":{
"p":0.8569069895,
"r":0.8494271686,
"f":0.8531506849
},
"agent":{
"p":0.9471830986,
"r":0.9641577061,
"f":0.9555950266
},
"dative":{
"p":0.8220720721,
"r":0.8371559633,
"f":0.8295454545
},
"acomp":{
"p":0.9371040724,
"r":0.9392290249,
"f":0.9381653454
},
"dep":{
"p":0.4218241042,
"r":0.4204545455,
"f":0.4211382114
},
"csubj":{
"p":0.865497076,
"r":0.875739645,
"f":0.8705882353
},
"quantmod":{
"p":0.8902847571,
"r":0.863525589,
"f":0.8767010309
},
"nmod":{
"p":0.8395759717,
"r":0.7239488117,
"f":0.777486911
},
"appos":{
"p":0.8256564787,
"r":0.8321041215,
"f":0.8288677615
},
"predet":{
"p":0.8537549407,
"r":0.9270386266,
"f":0.8888888889
},
"preconj":{
"p":0.6489361702,
"r":0.7093023256,
"f":0.6777777778
},
"oprd":{
"p":0.8913738019,
"r":0.8328358209,
"f":0.8611111111
},
"parataxis":{
"p":0.5842911877,
"r":0.6616052061,
"f":0.6205493388
},
"meta":{
"p":0.1808510638,
"r":0.6538461538,
"f":0.2833333333
},
"csubjpass":{
"p":1.0,
"r":0.8333333333,
"f":0.9090909091
}
},
"ents_per_type":{
"DATE":{
"p":0.8967681205,
"r":0.9073015873,
"f":0.9020041029
},
"GPE":{
"p":0.9559695174,
"r":0.9447698745,
"f":0.9503367003
},
"ORDINAL":{
"p":0.803030303,
"r":0.8229813665,
"f":0.8128834356
},
"ORG":{
"p":0.9044176707,
"r":0.8955461294,
"f":0.8999600373
},
"FAC":{
"p":0.544973545,
"r":0.7923076923,
"f":0.6457680251
},
"QUANTITY":{
"p":0.7828571429,
"r":0.7527472527,
"f":0.7675070028
},
"LOC":{
"p":0.8250825083,
"r":0.7961783439,
"f":0.8103727715
},
"CARDINAL":{
"p":0.8595769683,
"r":0.8697978597,
"f":0.8646572104
},
"PERSON":{
"p":0.9422647528,
"r":0.9640992167,
"f":0.9530569447
},
"NORP":{
"p":0.9249800479,
"r":0.9272,
"f":0.9260886936
},
"LAW":{
"p":0.5789473684,
"r":0.6875,
"f":0.6285714286
},
"PRODUCT":{
"p":0.6686746988,
"r":0.5260663507,
"f":0.5888594164
},
"TIME":{
"p":0.7287671233,
"r":0.7777777778,
"f":0.7524752475
},
"EVENT":{
"p":0.7443609023,
"r":0.5689655172,
"f":0.6449511401
},
"WORK_OF_ART":{
"p":0.5721925134,
"r":0.5515463918,
"f":0.56167979
},
"MONEY":{
"p":0.9120481928,
"r":0.893742621,
"f":0.9028026237
},
"PERCENT":{
"p":0.9164037855,
"r":0.8897396631,
"f":0.9028749029
},
"LANGUAGE":{
"p":1.0,
"r":0.75,
"f":0.8571428571
}
}
},
"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>=1.0.3,<1.1.0"
]
}