en_core_web_sm / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
22d7df0
raw history blame
No virus
10.1 kB
{
"lang":"en",
"name":"core_web_sm",
"version":"3.2.0",
"description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.2.0,<3.3.0",
"spacy_git_version":"bb26550e2",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"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"
],
"senter":[
"I",
"S"
],
"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":0.9993053983,
"token_p":0.9956742163,
"token_r":0.9957505887,
"token_f":0.9957124011,
"tag_acc":0.9725066923,
"sents_p":0.9205049471,
"sents_r":0.8899003892,
"sents_f":0.904943986,
"dep_uas":0.9166876131,
"dep_las":0.8979960057,
"dep_las_per_type":{
"prep":{
"p":0.8514792011,
"r":0.8605577689,
"f":0.8559944141
},
"det":{
"p":0.9776402069,
"r":0.9787164642,
"f":0.9781780395
},
"pobj":{
"p":0.9592170292,
"r":0.9679560181,
"f":0.9635667097
},
"nsubj":{
"p":0.9562219157,
"r":0.9416429354,
"f":0.9488764293
},
"aux":{
"p":0.9795809659,
"r":0.9822843408,
"f":0.9809307908
},
"advmod":{
"p":0.8570825239,
"r":0.8536934208,
"f":0.8553846154
},
"relcl":{
"p":0.7760869565,
"r":0.7772133527,
"f":0.7766497462
},
"root":{
"p":0.9174912987,
"r":0.8868658883,
"f":0.9019186905
},
"xcomp":{
"p":0.8794251665,
"r":0.9005743001,
"f":0.8898740912
},
"amod":{
"p":0.9157270416,
"r":0.9102688695,
"f":0.9129897979
},
"compound":{
"p":0.9140038367,
"r":0.9287146358,
"f":0.9213005166
},
"poss":{
"p":0.9734779988,
"r":0.9752415459,
"f":0.9743589744
},
"ccomp":{
"p":0.7639405204,
"r":0.8370672098,
"f":0.7988338192
},
"attr":{
"p":0.8959421454,
"r":0.9377628259,
"f":0.9163755907
},
"case":{
"p":0.9768015795,
"r":0.9904904905,
"f":0.9835984095
},
"mark":{
"p":0.9027518034,
"r":0.895336513,
"f":0.8990288679
},
"intj":{
"p":0.6757624398,
"r":0.6168498168,
"f":0.6449636155
},
"advcl":{
"p":0.6617760618,
"r":0.6474439688,
"f":0.6545315682
},
"cc":{
"p":0.8340149146,
"r":0.8293266356,
"f":0.8316641679
},
"neg":{
"p":0.949127182,
"r":0.9548419468,
"f":0.951975988
},
"conj":{
"p":0.7544115857,
"r":0.7803373615,
"f":0.7671554978
},
"nsubjpass":{
"p":0.9232776618,
"r":0.9071794872,
"f":0.9151577858
},
"auxpass":{
"p":0.9526362824,
"r":0.9712984055,
"f":0.9618768328
},
"dobj":{
"p":0.9192971544,
"r":0.9422264722,
"f":0.9306205974
},
"nummod":{
"p":0.9373881932,
"r":0.9262626263,
"f":0.9317922012
},
"npadvmod":{
"p":0.7576675502,
"r":0.7108348135,
"f":0.7335043988
},
"prt":{
"p":0.8091728092,
"r":0.8853046595,
"f":0.8455284553
},
"pcomp":{
"p":0.871398454,
"r":0.8683473389,
"f":0.869870221
},
"expl":{
"p":0.9808917197,
"r":0.9892933619,
"f":0.9850746269
},
"acl":{
"p":0.7457627119,
"r":0.6961265685,
"f":0.7200902935
},
"agent":{
"p":0.8868243243,
"r":0.9408602151,
"f":0.9130434783
},
"dative":{
"p":0.7659033079,
"r":0.6903669725,
"f":0.7261761158
},
"acomp":{
"p":0.9110499771,
"r":0.9011337868,
"f":0.9060647515
},
"dep":{
"p":0.4232365145,
"r":0.1655844156,
"f":0.2380396733
},
"csubj":{
"p":0.7077922078,
"r":0.6449704142,
"f":0.6749226006
},
"quantmod":{
"p":0.8597883598,
"r":0.7920389927,
"f":0.8245243129
},
"nmod":{
"p":0.7614091273,
"r":0.5795246801,
"f":0.6581314879
},
"appos":{
"p":0.6951055231,
"r":0.6715835141,
"f":0.6831421006
},
"predet":{
"p":0.8273092369,
"r":0.8841201717,
"f":0.8547717842
},
"preconj":{
"p":0.5504587156,
"r":0.6976744186,
"f":0.6153846154
},
"oprd":{
"p":0.821192053,
"r":0.7402985075,
"f":0.7786499215
},
"parataxis":{
"p":0.6215469613,
"r":0.4880694143,
"f":0.5467800729
},
"meta":{
"p":0.8095238095,
"r":0.3269230769,
"f":0.4657534247
},
"csubjpass":{
"p":0.6,
"r":0.5,
"f":0.5454545455
}
},
"ents_p":0.8463095057,
"ents_r":0.8377904647,
"ents_f":0.8420284384,
"ents_per_type":{
"DATE":{
"p":0.8653725736,
"r":0.8774603175,
"f":0.8713745271
},
"GPE":{
"p":0.9126848692,
"r":0.8951185495,
"f":0.9038163639
},
"ORDINAL":{
"p":0.7818696884,
"r":0.8571428571,
"f":0.8177777778
},
"ORG":{
"p":0.8032096817,
"r":0.8093849417,
"f":0.8062854879
},
"FAC":{
"p":0.412371134,
"r":0.3076923077,
"f":0.3524229075
},
"CARDINAL":{
"p":0.8206857785,
"r":0.8680142687,
"f":0.8436867957
},
"PERSON":{
"p":0.8429059298,
"r":0.8860966057,
"f":0.8639618138
},
"NORP":{
"p":0.8995176849,
"r":0.8952,
"f":0.8973536488
},
"LOC":{
"p":0.7210144928,
"r":0.6337579618,
"f":0.6745762712
},
"TIME":{
"p":0.7492163009,
"r":0.6988304094,
"f":0.7231467474
},
"QUANTITY":{
"p":0.8273381295,
"r":0.6318681319,
"f":0.7165109034
},
"EVENT":{
"p":0.5604395604,
"r":0.2931034483,
"f":0.3849056604
},
"WORK_OF_ART":{
"p":0.5151515152,
"r":0.3505154639,
"f":0.4171779141
},
"MONEY":{
"p":0.9178743961,
"r":0.8972845336,
"f":0.9074626866
},
"LAW":{
"p":0.5102040816,
"r":0.390625,
"f":0.4424778761
},
"PERCENT":{
"p":0.9230769231,
"r":0.8820826953,
"f":0.9021143305
},
"PRODUCT":{
"p":0.5185185185,
"r":0.1990521327,
"f":0.2876712329
},
"LANGUAGE":{
"p":0.7826086957,
"r":0.5625,
"f":0.6545454545
}
},
"speed":8030.19594793
},
"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"
}
],
"requirements":[
]
}