en_core_web_lg / meta.json
EC2 Default User
Update spaCy pipeline
1d03e65
raw
history blame
10.3 kB
{
"lang":"en",
"name":"core_web_lg",
"version":"3.3.0",
"description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"[email protected]",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.3.0.dev0,<3.4.0",
"spacy_git_version":"849bef2de",
"vectors":{
"width":300,
"vectors":342918,
"keys":684830,
"name":"en_vectors"
},
"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",
"``"
],
"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":[
"tok2vec",
"tagger",
"parser",
"attribute_ruler",
"lemmatizer",
"ner"
],
"components":[
"tok2vec",
"tagger",
"parser",
"senter",
"attribute_ruler",
"lemmatizer",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9993092439,
"token_p":0.9956819193,
"token_r":0.9957659295,
"token_f":0.9957239226,
"tag_acc":0.9738145328,
"sents_p":0.9177103185,
"sents_r":0.8894386173,
"sents_f":0.9033533215,
"dep_uas":0.9188508811,
"dep_las":0.9008477499,
"dep_las_per_type":{
"prep":{
"p":0.8537864878,
"r":0.8645418327,
"f":0.8591305004
},
"det":{
"p":0.9790682522,
"r":0.9802658403,
"f":0.9796666802
},
"pobj":{
"p":0.9633579437,
"r":0.9684272531,
"f":0.965885947
},
"nsubj":{
"p":0.9564757243,
"r":0.9502738226,
"f":0.9533646873
},
"aux":{
"p":0.9809760868,
"r":0.9823733642,
"f":0.9816742283
},
"advmod":{
"p":0.8550492715,
"r":0.8541140838,
"f":0.8545814218
},
"relcl":{
"p":0.7709000356,
"r":0.7862844702,
"f":0.7785162565
},
"root":{
"p":0.9183576195,
"r":0.889702487,
"f":0.9038029821
},
"xcomp":{
"p":0.882620883,
"r":0.9041636755,
"f":0.8932624113
},
"amod":{
"p":0.9195970101,
"r":0.9166180758,
"f":0.9181051265
},
"compound":{
"p":0.9193539526,
"r":0.9320004455,
"f":0.9256340054
},
"poss":{
"p":0.9711422846,
"r":0.9754428341,
"f":0.9732878088
},
"ccomp":{
"p":0.7727868239,
"r":0.8409368635,
"f":0.8054228031
},
"attr":{
"p":0.8955042527,
"r":0.9297729184,
"f":0.912316897
},
"case":{
"p":0.9758144126,
"r":0.9894894895,
"f":0.9826043738
},
"mark":{
"p":0.9062829989,
"r":0.9096449391,
"f":0.9079608569
},
"intj":{
"p":0.6653322658,
"r":0.6087912088,
"f":0.635807192
},
"advcl":{
"p":0.6779661017,
"r":0.6648199446,
"f":0.6713286713
},
"cc":{
"p":0.8292624233,
"r":0.824303313,
"f":0.8267754319
},
"neg":{
"p":0.9393336648,
"r":0.9478173608,
"f":0.9435564436
},
"conj":{
"p":0.763665795,
"r":0.7720292044,
"f":0.7678247261
},
"nsubjpass":{
"p":0.9263266358,
"r":0.9220512821,
"f":0.9241840144
},
"auxpass":{
"p":0.9499329459,
"r":0.9681093394,
"f":0.9589350181
},
"dobj":{
"p":0.926432648,
"r":0.9442983505,
"f":0.9352801894
},
"nummod":{
"p":0.9362134689,
"r":0.9303030303,
"f":0.9332488917
},
"npadvmod":{
"p":0.7723030982,
"r":0.734991119,
"f":0.753185293
},
"prt":{
"p":0.8160066007,
"r":0.8862007168,
"f":0.8496563574
},
"pcomp":{
"p":0.8800841515,
"r":0.8788515406,
"f":0.8794674142
},
"expl":{
"p":0.9809322034,
"r":0.9914346895,
"f":0.9861554846
},
"acl":{
"p":0.7556456283,
"r":0.7119476268,
"f":0.7331460674
},
"agent":{
"p":0.8991452991,
"r":0.9426523297,
"f":0.9203849519
},
"dative":{
"p":0.810298103,
"r":0.6857798165,
"f":0.7428571429
},
"acomp":{
"p":0.9111721612,
"r":0.9024943311,
"f":0.9068124858
},
"dep":{
"p":0.3930131004,
"r":0.1461038961,
"f":0.2130177515
},
"csubj":{
"p":0.7068965517,
"r":0.7278106509,
"f":0.7172011662
},
"quantmod":{
"p":0.8746594005,
"r":0.7822908205,
"f":0.8259005146
},
"nmod":{
"p":0.7651217596,
"r":0.5935405241,
"f":0.6684969115
},
"appos":{
"p":0.6994459834,
"r":0.6572668113,
"f":0.6777007381
},
"predet":{
"p":0.8380566802,
"r":0.8884120172,
"f":0.8625
},
"preconj":{
"p":0.537037037,
"r":0.6744186047,
"f":0.5979381443
},
"oprd":{
"p":0.8477508651,
"r":0.7313432836,
"f":0.7852564103
},
"parataxis":{
"p":0.6187845304,
"r":0.4859002169,
"f":0.5443499392
},
"meta":{
"p":1.0,
"r":0.3269230769,
"f":0.4927536232
},
"csubjpass":{
"p":0.5555555556,
"r":0.8333333333,
"f":0.6666666667
}
},
"ents_p":0.8602117695,
"ents_r":0.8462540064,
"ents_f":0.8531758053,
"ents_per_type":{
"DATE":{
"p":0.872593068,
"r":0.8631746032,
"f":0.8678582828
},
"GPE":{
"p":0.9257256688,
"r":0.9073919107,
"f":0.916467108
},
"ORDINAL":{
"p":0.787965616,
"r":0.8540372671,
"f":0.8196721311
},
"ORG":{
"p":0.8203309693,
"r":0.8279427359,
"f":0.8241192769
},
"CARDINAL":{
"p":0.8304398148,
"r":0.8531510107,
"f":0.8416422287
},
"PERSON":{
"p":0.8953229399,
"r":0.9184073107,
"f":0.9067182214
},
"NORP":{
"p":0.8794048551,
"r":0.8984,
"f":0.8888009497
},
"LOC":{
"p":0.7147766323,
"r":0.6624203822,
"f":0.6876033058
},
"FAC":{
"p":0.3949579832,
"r":0.3615384615,
"f":0.3775100402
},
"TIME":{
"p":0.71875,
"r":0.6725146199,
"f":0.6948640483
},
"QUANTITY":{
"p":0.8014184397,
"r":0.6208791209,
"f":0.6996904025
},
"EVENT":{
"p":0.6354166667,
"r":0.3505747126,
"f":0.4518518519
},
"WORK_OF_ART":{
"p":0.5,
"r":0.3092783505,
"f":0.3821656051
},
"MONEY":{
"p":0.9039145907,
"r":0.8996458087,
"f":0.9017751479
},
"LAW":{
"p":0.6428571429,
"r":0.421875,
"f":0.5094339623
},
"PERCENT":{
"p":0.9187898089,
"r":0.8836140888,
"f":0.9008587041
},
"LANGUAGE":{
"p":0.75,
"r":0.65625,
"f":0.7
},
"PRODUCT":{
"p":0.6097560976,
"r":0.2369668246,
"f":0.3412969283
}
},
"speed":7281.6726563626
},
"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":"GloVe Common Crawl",
"url":"https://nlp.stanford.edu/projects/glove/",
"license":"Public Domain Dedication and License v1.0",
"author":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning"
}
],
"requirements":[
]
}