en_core_web_sm / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
8957c28
{
"lang":"en",
"name":"core_web_sm",
"version":"3.3.0",
"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":">=3.3.0.dev0,<3.4.0",
"spacy_git_version":"849bef2de",
"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"
],
"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":0.9726545475,
"sents_p":0.9188657486,
"sents_r":0.8935285969,
"sents_f":0.9060200669,
"dep_uas":0.9180803841,
"dep_las":0.8996666011,
"dep_las_per_type":{
"prep":{
"p":0.8545638793,
"r":0.8639347372,
"f":0.8592237589
},
"det":{
"p":0.9767252604,
"r":0.9787164642,
"f":0.9777198485
},
"pobj":{
"p":0.9624306803,
"r":0.9677596701,
"f":0.9650878189
},
"nsubj":{
"p":0.9570163789,
"r":0.9471631982,
"f":0.9520642959
},
"aux":{
"p":0.9800017776,
"r":0.9815721535,
"f":0.980786337
},
"advmod":{
"p":0.8575166709,
"r":0.8547030119,
"f":0.8561075296
},
"relcl":{
"p":0.7630824373,
"r":0.7724963716,
"f":0.7677605481
},
"root":{
"p":0.9153887909,
"r":0.8899663566,
"f":0.9024985785
},
"xcomp":{
"p":0.8755679832,
"r":0.8991385499,
"f":0.8871967416
},
"amod":{
"p":0.9161676647,
"r":0.9119533528,
"f":0.9140556512
},
"compound":{
"p":0.9153947513,
"r":0.9285475607,
"f":0.9219242466
},
"poss":{
"p":0.9729241877,
"r":0.9764492754,
"f":0.9746835443
},
"ccomp":{
"p":0.7720643231,
"r":0.8409368635,
"f":0.8050302203
},
"attr":{
"p":0.9093147312,
"r":0.9318755257,
"f":0.9204569055
},
"case":{
"p":0.977799704,
"r":0.991991992,
"f":0.9848447205
},
"mark":{
"p":0.9035921817,
"r":0.9064652888,
"f":0.905026455
},
"intj":{
"p":0.6711250983,
"r":0.6249084249,
"f":0.6471927162
},
"advcl":{
"p":0.6756965944,
"r":0.6595316041,
"f":0.6675162482
},
"cc":{
"p":0.8375451264,
"r":0.8324363114,
"f":0.8349829044
},
"neg":{
"p":0.9480778832,
"r":0.9528349222,
"f":0.9504504505
},
"conj":{
"p":0.7654719087,
"r":0.77693857,
"f":0.7711626164
},
"nsubjpass":{
"p":0.9168804515,
"r":0.9164102564,
"f":0.9166452937
},
"auxpass":{
"p":0.9459821429,
"r":0.9653758542,
"f":0.9555806088
},
"dobj":{
"p":0.9223308565,
"r":0.9396764682,
"f":0.9309228705
},
"nummod":{
"p":0.9368956743,
"r":0.9297979798,
"f":0.9333333333
},
"npadvmod":{
"p":0.7781178271,
"r":0.7225577265,
"f":0.7493092651
},
"prt":{
"p":0.816091954,
"r":0.8906810036,
"f":0.851756641
},
"pcomp":{
"p":0.8699300699,
"r":0.8711484594,
"f":0.8705388383
},
"expl":{
"p":0.983014862,
"r":0.9914346895,
"f":0.987206823
},
"acl":{
"p":0.7332949309,
"r":0.6944899073,
"f":0.7133650883
},
"agent":{
"p":0.8885135135,
"r":0.9426523297,
"f":0.9147826087
},
"dative":{
"p":0.7847769029,
"r":0.6857798165,
"f":0.7319461444
},
"acomp":{
"p":0.9046746104,
"r":0.8952380952,
"f":0.8999316161
},
"dep":{
"p":0.4151624549,
"r":0.1866883117,
"f":0.2575587906
},
"csubj":{
"p":0.6476683938,
"r":0.7396449704,
"f":0.6906077348
},
"quantmod":{
"p":0.8682310469,
"r":0.7814784728,
"f":0.8225737495
},
"nmod":{
"p":0.741078208,
"r":0.5947592931,
"f":0.6599053414
},
"appos":{
"p":0.7215189873,
"r":0.6676789588,
"f":0.6935556557
},
"predet":{
"p":0.8395061728,
"r":0.8755364807,
"f":0.8571428571
},
"preconj":{
"p":0.5544554455,
"r":0.6511627907,
"f":0.5989304813
},
"oprd":{
"p":0.8205980066,
"r":0.7373134328,
"f":0.7767295597
},
"parataxis":{
"p":0.6121883657,
"r":0.4793926247,
"f":0.5377128954
},
"meta":{
"p":0.7407407407,
"r":0.3846153846,
"f":0.5063291139
},
"csubjpass":{
"p":0.7142857143,
"r":0.8333333333,
"f":0.7692307692
}
},
"ents_p":0.8508041869,
"ents_r":0.8344851763,
"ents_f":0.8425656714,
"ents_per_type":{
"DATE":{
"p":0.8732394366,
"r":0.866031746,
"f":0.8696206567
},
"GPE":{
"p":0.9154443486,
"r":0.8878661088,
"f":0.90144435
},
"ORDINAL":{
"p":0.7927927928,
"r":0.8198757764,
"f":0.8061068702
},
"FAC":{
"p":0.4049586777,
"r":0.3769230769,
"f":0.390438247
},
"ORG":{
"p":0.8038601982,
"r":0.8170731707,
"f":0.810412832
},
"CARDINAL":{
"p":0.8222477064,
"r":0.8525564804,
"f":0.8371278459
},
"LOC":{
"p":0.714801444,
"r":0.6305732484,
"f":0.6700507614
},
"PERSON":{
"p":0.8572793883,
"r":0.8782637076,
"f":0.8676446881
},
"NORP":{
"p":0.918652424,
"r":0.8944,
"f":0.9063640049
},
"TIME":{
"p":0.7436708861,
"r":0.6871345029,
"f":0.7142857143
},
"QUANTITY":{
"p":0.8308823529,
"r":0.6208791209,
"f":0.7106918239
},
"EVENT":{
"p":0.5533980583,
"r":0.3275862069,
"f":0.4115523466
},
"WORK_OF_ART":{
"p":0.4926470588,
"r":0.3453608247,
"f":0.4060606061
},
"LAW":{
"p":0.58,
"r":0.453125,
"f":0.5087719298
},
"MONEY":{
"p":0.9198564593,
"r":0.9079102715,
"f":0.9138443256
},
"PERCENT":{
"p":0.9153354633,
"r":0.8774885145,
"f":0.8960125098
},
"LANGUAGE":{
"p":0.7857142857,
"r":0.6875,
"f":0.7333333333
},
"PRODUCT":{
"p":0.5795454545,
"r":0.2417061611,
"f":0.3411371237
}
},
"speed":9738.3022066337
},
"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":[
]
}