en_core_web_sm / meta.json
NimmyhBas's picture
Update spaCy pipeline
7d6af26 verified
{
"lang":"en",
"name":"core_web_sm",
"version":"3.7.1",
"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":">=3.7.2,<3.8.0",
"spacy_git_version":"bd2c17e20",
"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",
"_SP",
"``"
],
"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":0.9986194413,
"token_p":0.9956819193,
"token_r":0.9957659295,
"token_f":0.9957239226,
"tag_acc":0.97246532,
"sents_p":0.9201877934,
"sents_r":0.8921432812,
"sents_f":0.9059485531,
"dep_uas":0.9175304332,
"dep_las":0.89874821,
"dep_las_per_type":{
"prep":{
"p":0.853521338,
"r":0.8635932461,
"f":0.8585277532
},
"det":{
"p":0.9763930156,
"r":0.9781048683,
"f":0.9772481923
},
"pobj":{
"p":0.9613764045,
"r":0.967681131,
"f":0.9645184649
},
"nsubj":{
"p":0.9565737052,
"r":0.9467250821,
"f":0.9516239128
},
"aux":{
"p":0.9815061794,
"r":0.9827294578,
"f":0.9821174377
},
"advmod":{
"p":0.8548033091,
"r":0.8519266364,
"f":0.8533625485
},
"relcl":{
"p":0.7571736011,
"r":0.7659651669,
"f":0.7615440115
},
"root":{
"p":0.9195942266,
"r":0.8910218352,
"f":0.9050825879
},
"xcomp":{
"p":0.8836222144,
"r":0.8966259871,
"f":0.8900766079
},
"amod":{
"p":0.9174389766,
"r":0.9107223842,
"f":0.9140683422
},
"compound":{
"p":0.9126489559,
"r":0.9298284696,
"f":0.9211586207
},
"poss":{
"p":0.9739583333,
"r":0.9786634461,
"f":0.9763052209
},
"ccomp":{
"p":0.7671207315,
"r":0.8372708758,
"f":0.8006621872
},
"attr":{
"p":0.899837794,
"r":0.93313709,
"f":0.9161849711
},
"case":{
"p":0.9787549407,
"r":0.9914914915,
"f":0.9850820487
},
"mark":{
"p":0.9068783069,
"r":0.9083200848,
"f":0.9075986232
},
"intj":{
"p":0.6717131474,
"r":0.6175824176,
"f":0.6435114504
},
"advcl":{
"p":0.6633986928,
"r":0.6645681189,
"f":0.6639828909
},
"cc":{
"p":0.8323511726,
"r":0.8277717976,
"f":0.8300551691
},
"neg":{
"p":0.9466865969,
"r":0.9533366784,
"f":0.95
},
"conj":{
"p":0.7567333828,
"r":0.7710221551,
"f":0.763810949
},
"nsubjpass":{
"p":0.9182939363,
"r":0.9164102564,
"f":0.9173511294
},
"auxpass":{
"p":0.9501335708,
"r":0.9722095672,
"f":0.9610448097
},
"dobj":{
"p":0.9229805886,
"r":0.9396764682,
"f":0.9312537019
},
"nummod":{
"p":0.9379292801,
"r":0.9310606061,
"f":0.9344823216
},
"npadvmod":{
"p":0.7629658087,
"r":0.7055062167,
"f":0.7331118494
},
"prt":{
"p":0.8118323747,
"r":0.8853046595,
"f":0.8469781397
},
"pcomp":{
"p":0.8835714286,
"r":0.8662464986,
"f":0.8748231966
},
"expl":{
"p":0.9851380042,
"r":0.9935760171,
"f":0.9893390192
},
"acl":{
"p":0.742010459,
"r":0.6966721222,
"f":0.7186268993
},
"agent":{
"p":0.9034482759,
"r":0.9390681004,
"f":0.920913884
},
"dative":{
"p":0.8,
"r":0.6972477064,
"f":0.7450980392
},
"acomp":{
"p":0.9020594966,
"r":0.893877551,
"f":0.8979498861
},
"dep":{
"p":0.4147286822,
"r":0.1737012987,
"f":0.2448512586
},
"csubj":{
"p":0.6983240223,
"r":0.7396449704,
"f":0.7183908046
},
"quantmod":{
"p":0.8727436823,
"r":0.7855402112,
"f":0.8268490808
},
"nmod":{
"p":0.7498033045,
"r":0.5807434491,
"f":0.654532967
},
"appos":{
"p":0.7048498845,
"r":0.6620390456,
"f":0.6827740492
},
"predet":{
"p":0.8299595142,
"r":0.8798283262,
"f":0.8541666667
},
"preconj":{
"p":0.5544554455,
"r":0.6511627907,
"f":0.5989304813
},
"oprd":{
"p":0.8013245033,
"r":0.7223880597,
"f":0.759811617
},
"parataxis":{
"p":0.6428571429,
"r":0.4880694143,
"f":0.5548705302
},
"meta":{
"p":0.3770491803,
"r":0.4423076923,
"f":0.407079646
},
"csubjpass":{
"p":0.5555555556,
"r":0.8333333333,
"f":0.6666666667
}
},
"ents_p":0.8454836771,
"ents_r":0.8456530449,
"ents_f":0.8455683525,
"ents_per_type":{
"DATE":{
"p":0.8603213844,
"r":0.8838095238,
"f":0.8719072972
},
"GPE":{
"p":0.9146932953,
"r":0.8942817294,
"f":0.9043723554
},
"ORG":{
"p":0.7955942623,
"r":0.8234358431,
"f":0.8092756644
},
"CARDINAL":{
"p":0.8149171271,
"r":0.8769322235,
"f":0.8447880871
},
"PERSON":{
"p":0.8617758186,
"r":0.8932767624,
"f":0.8772435897
},
"NORP":{
"p":0.8957006369,
"r":0.9,
"f":0.8978451716
},
"ORDINAL":{
"p":0.7844827586,
"r":0.847826087,
"f":0.8149253731
},
"QUANTITY":{
"p":0.8529411765,
"r":0.6373626374,
"f":0.7295597484
},
"LOC":{
"p":0.7210884354,
"r":0.6751592357,
"f":0.6973684211
},
"FAC":{
"p":0.358490566,
"r":0.2923076923,
"f":0.3220338983
},
"TIME":{
"p":0.7413793103,
"r":0.7543859649,
"f":0.747826087
},
"PRODUCT":{
"p":0.5591397849,
"r":0.2464454976,
"f":0.3421052632
},
"WORK_OF_ART":{
"p":0.4885496183,
"r":0.3298969072,
"f":0.3938461538
},
"EVENT":{
"p":0.6428571429,
"r":0.3103448276,
"f":0.4186046512
},
"MONEY":{
"p":0.9071428571,
"r":0.8996458087,
"f":0.9033787789
},
"LAW":{
"p":0.5454545455,
"r":0.46875,
"f":0.5042016807
},
"PERCENT":{
"p":0.9184,
"r":0.8790199081,
"f":0.8982785603
},
"LANGUAGE":{
"p":0.8,
"r":0.625,
"f":0.701754386
}
},
"speed":7920.0598120459
},
"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":[
]
}