en_core_web_trf / meta.json
adrianeboyd's picture
Update spaCy pipeline
a134d22
raw
history blame
10.4 kB
{
"lang":"en",
"name":"core_web_trf",
"version":"3.5.0",
"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":">=3.5.0,<3.6.0",
"spacy_git_version":"9e0322de1",
"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":0.9986194413,
"token_p":0.9956819193,
"token_r":0.9957659295,
"token_f":0.9957239226,
"tag_acc":0.9778773818,
"sents_p":0.9503875969,
"sents_r":0.8491984959,
"sents_f":0.8969481605,
"dep_uas":0.9527427739,
"dep_las":0.9395456671,
"dep_las_per_type":{
"prep":{
"p":0.9243897824,
"r":0.9268450009,
"f":0.9256157635
},
"det":{
"p":0.9903740262,
"r":0.990010601,
"f":0.9901922802
},
"pobj":{
"p":0.9844203752,
"r":0.9850775574,
"f":0.9847488567
},
"nsubj":{
"p":0.9805339997,
"r":0.9798466594,
"f":0.9801902091
},
"aux":{
"p":0.9880814729,
"r":0.9889610968,
"f":0.9885210892
},
"advmod":{
"p":0.8982352941,
"r":0.8992932862,
"f":0.8987639788
},
"relcl":{
"p":0.8786803831,
"r":0.898766328,
"f":0.8886098655
},
"root":{
"p":0.9681063123,
"r":0.8650306748,
"f":0.9136705686
},
"xcomp":{
"p":0.9437432384,
"r":0.9393395549,
"f":0.9415362475
},
"amod":{
"p":0.9438063721,
"r":0.9423388403,
"f":0.9430720353
},
"compound":{
"p":0.9517433752,
"r":0.950100245,
"f":0.9509211003
},
"poss":{
"p":0.9875426964,
"r":0.989331723,
"f":0.9884364002
},
"ccomp":{
"p":0.8524404086,
"r":0.9177189409,
"f":0.8838760298
},
"attr":{
"p":0.9554723263,
"r":0.9655172414,
"f":0.9604685212
},
"case":{
"p":0.9885515182,
"r":0.993993994,
"f":0.9912652857
},
"mark":{
"p":0.950065703,
"r":0.9578696343,
"f":0.9539517087
},
"intj":{
"p":0.6128461992,
"r":0.7619047619,
"f":0.6792945787
},
"advcl":{
"p":0.8079774994,
"r":0.7957693276,
"f":0.8018269475
},
"cc":{
"p":0.8930443068,
"r":0.8967826815,
"f":0.89490959
},
"neg":{
"p":0.9629258517,
"r":0.9643753136,
"f":0.9636500376
},
"conj":{
"p":0.8663254374,
"r":0.916163142,
"f":0.8905475681
},
"nsubjpass":{
"p":0.9555214724,
"r":0.9584615385,
"f":0.9569892473
},
"auxpass":{
"p":0.9675236806,
"r":0.9772209567,
"f":0.9723481414
},
"dobj":{
"p":0.9736800128,
"r":0.97282652,
"f":0.9732530793
},
"nummod":{
"p":0.9586312564,
"r":0.947979798,
"f":0.9532757745
},
"npadvmod":{
"p":0.8557833089,
"r":0.8305506217,
"f":0.8429781864
},
"prt":{
"p":0.8916299559,
"r":0.9068100358,
"f":0.8991559307
},
"pcomp":{
"p":0.9331926864,
"r":0.9292717087,
"f":0.9312280702
},
"expl":{
"p":0.9935760171,
"r":0.9935760171,
"f":0.9935760171
},
"acl":{
"p":0.8561230093,
"r":0.8505182761,
"f":0.8533114395
},
"agent":{
"p":0.9543859649,
"r":0.9749103943,
"f":0.9645390071
},
"dative":{
"p":0.8498845266,
"r":0.8440366972,
"f":0.8469505178
},
"acomp":{
"p":0.939462904,
"r":0.9360544218,
"f":0.9377555657
},
"dep":{
"p":0.4197730956,
"r":0.4204545455,
"f":0.4201135442
},
"csubj":{
"p":0.901734104,
"r":0.9230769231,
"f":0.9122807018
},
"quantmod":{
"p":0.8879598662,
"r":0.8627132413,
"f":0.8751545117
},
"nmod":{
"p":0.8340277778,
"r":0.7318708105,
"f":0.7796170075
},
"appos":{
"p":0.8211346903,
"r":0.8225596529,
"f":0.821846554
},
"predet":{
"p":0.8473895582,
"r":0.9055793991,
"f":0.8755186722
},
"preconj":{
"p":0.6526315789,
"r":0.7209302326,
"f":0.6850828729
},
"oprd":{
"p":0.8861538462,
"r":0.8597014925,
"f":0.8727272727
},
"parataxis":{
"p":0.6038461538,
"r":0.6811279826,
"f":0.6401630989
},
"meta":{
"p":0.1724137931,
"r":0.6730769231,
"f":0.2745098039
},
"csubjpass":{
"p":1.0,
"r":0.8333333333,
"f":0.9090909091
}
},
"ents_p":0.8977938984,
"ents_r":0.9048978365,
"ents_f":0.9013318701,
"ents_per_type":{
"DATE":{
"p":0.8915360502,
"r":0.9028571429,
"f":0.8971608833
},
"GPE":{
"p":0.9549524342,
"r":0.9520223152,
"f":0.9534851236
},
"ORDINAL":{
"p":0.7771260997,
"r":0.8229813665,
"f":0.7993966817
},
"ORG":{
"p":0.8985736926,
"r":0.9019088017,
"f":0.9002381582
},
"FAC":{
"p":0.5635359116,
"r":0.7846153846,
"f":0.6559485531
},
"QUANTITY":{
"p":0.7823529412,
"r":0.7307692308,
"f":0.7556818182
},
"LOC":{
"p":0.8443708609,
"r":0.8121019108,
"f":0.8279220779
},
"CARDINAL":{
"p":0.8491208168,
"r":0.8900118906,
"f":0.8690856313
},
"PERSON":{
"p":0.9398162813,
"r":0.9683420366,
"f":0.953865938
},
"NORP":{
"p":0.9253968254,
"r":0.9328,
"f":0.9290836653
},
"PRODUCT":{
"p":0.6804733728,
"r":0.5450236967,
"f":0.6052631579
},
"TIME":{
"p":0.7663043478,
"r":0.8245614035,
"f":0.7943661972
},
"EVENT":{
"p":0.7898550725,
"r":0.6264367816,
"f":0.6987179487
},
"WORK_OF_ART":{
"p":0.6514285714,
"r":0.587628866,
"f":0.6178861789
},
"LAW":{
"p":0.6363636364,
"r":0.65625,
"f":0.6461538462
},
"MONEY":{
"p":0.9109506619,
"r":0.893742621,
"f":0.9022646007
},
"PERCENT":{
"p":0.9224683544,
"r":0.8928024502,
"f":0.9073929961
},
"LANGUAGE":{
"p":1.0,
"r":0.71875,
"f":0.8363636364
}
},
"speed":6031.0542416801
},
"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>=1.2.0.dev0,<1.3.0"
]
}