en_core_web_md / meta.json
Adriane Boyd
Update spaCy pipeline
15db25f
raw
history blame
10.3 kB
{
"lang":"en",
"name":"core_web_md",
"version":"3.4.0",
"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":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"vectors":{
"width":300,
"vectors":20000,
"keys":514157,
"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",
"_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":0.9993092439,
"token_p":0.9956819193,
"token_r":0.9957659295,
"token_f":0.9957239226,
"tag_acc":0.9727809676,
"sents_p":0.9227998641,
"sents_r":0.8957714889,
"sents_f":0.9090848229,
"dep_uas":0.9208996725,
"dep_las":0.9025794107,
"dep_las_per_type":{
"prep":{
"p":0.8615940393,
"r":0.8687535572,
"f":0.8651589866
},
"det":{
"p":0.9788101059,
"r":0.9793688331,
"f":0.9790893898
},
"pobj":{
"p":0.9638667292,
"r":0.9679167485,
"f":0.9658874934
},
"nsubj":{
"p":0.9573857364,
"r":0.9498357065,
"f":0.9535957774
},
"aux":{
"p":0.9798669623,
"r":0.9835306686,
"f":0.9816953972
},
"advmod":{
"p":0.8569501812,
"r":0.8552919401,
"f":0.8561202577
},
"relcl":{
"p":0.776330076,
"r":0.7783018868,
"f":0.7773147309
},
"root":{
"p":0.9218431426,
"r":0.8947819777,
"f":0.9081110032
},
"xcomp":{
"p":0.8827247191,
"r":0.9023689878,
"f":0.8924387646
},
"amod":{
"p":0.9168349072,
"r":0.9120829284,
"f":0.9144527444
},
"compound":{
"p":0.9189753738,
"r":0.9310536868,
"f":0.9249751024
},
"poss":{
"p":0.972745491,
"r":0.9770531401,
"f":0.9748945571
},
"ccomp":{
"p":0.7827560241,
"r":0.8468431772,
"f":0.8135394248
},
"attr":{
"p":0.9095744681,
"r":0.9348191758,
"f":0.9220240564
},
"case":{
"p":0.9782501236,
"r":0.9904904905,
"f":0.9843322557
},
"mark":{
"p":0.9012023001,
"r":0.9136195019,
"f":0.9073684211
},
"intj":{
"p":0.6692975533,
"r":0.6212454212,
"f":0.6443768997
},
"advcl":{
"p":0.6774029926,
"r":0.6726265424,
"f":0.6750063179
},
"cc":{
"p":0.8407015858,
"r":0.8369812223,
"f":0.838837279
},
"neg":{
"p":0.9451097804,
"r":0.9503261415,
"f":0.9477107831
},
"conj":{
"p":0.7748971706,
"r":0.7826032226,
"f":0.778731133
},
"nsubjpass":{
"p":0.9196108551,
"r":0.921025641,
"f":0.9203177043
},
"auxpass":{
"p":0.9491525424,
"r":0.969476082,
"f":0.9592066712
},
"dobj":{
"p":0.9284929356,
"r":0.9426249104,
"f":0.9355055558
},
"nummod":{
"p":0.9416857652,
"r":0.9338383838,
"f":0.9377456574
},
"npadvmod":{
"p":0.7796163971,
"r":0.7364120782,
"f":0.7573986116
},
"prt":{
"p":0.8156606852,
"r":0.8960573477,
"f":0.853970965
},
"pcomp":{
"p":0.8794926004,
"r":0.8739495798,
"f":0.8767123288
},
"expl":{
"p":0.9809322034,
"r":0.9914346895,
"f":0.9861554846
},
"acl":{
"p":0.7488505747,
"r":0.7108565194,
"f":0.729359082
},
"agent":{
"p":0.889632107,
"r":0.9534050179,
"f":0.9204152249
},
"dative":{
"p":0.7918918919,
"r":0.6720183486,
"f":0.7270471464
},
"acomp":{
"p":0.9041970803,
"r":0.8988662132,
"f":0.9015237662
},
"dep":{
"p":0.3385093168,
"r":0.1769480519,
"f":0.2324093817
},
"csubj":{
"p":0.6983240223,
"r":0.7396449704,
"f":0.7183908046
},
"quantmod":{
"p":0.8521434821,
"r":0.791226645,
"f":0.8205560236
},
"nmod":{
"p":0.7608359133,
"r":0.5990249848,
"f":0.6703034436
},
"appos":{
"p":0.7089244851,
"r":0.6720173536,
"f":0.6899777283
},
"predet":{
"p":0.8380566802,
"r":0.8884120172,
"f":0.8625
},
"preconj":{
"p":0.5463917526,
"r":0.6162790698,
"f":0.5792349727
},
"oprd":{
"p":0.8697183099,
"r":0.7373134328,
"f":0.7980613893
},
"parataxis":{
"p":0.5855614973,
"r":0.4750542299,
"f":0.5245508982
},
"meta":{
"p":0.7714285714,
"r":0.5192307692,
"f":0.6206896552
},
"csubjpass":{
"p":0.4545454545,
"r":0.8333333333,
"f":0.5882352941
}
},
"ents_p":0.8644910088,
"ents_r":0.8450520833,
"ents_f":0.8546610277,
"ents_per_type":{
"DATE":{
"p":0.8751191611,
"r":0.8742857143,
"f":0.8747022392
},
"GPE":{
"p":0.9322571346,
"r":0.9020920502,
"f":0.9169265665
},
"ORDINAL":{
"p":0.7808988764,
"r":0.8633540373,
"f":0.8200589971
},
"FAC":{
"p":0.390625,
"r":0.3846153846,
"f":0.3875968992
},
"ORG":{
"p":0.8222987288,
"r":0.8231707317,
"f":0.8227344992
},
"QUANTITY":{
"p":0.8310810811,
"r":0.6758241758,
"f":0.7454545455
},
"CARDINAL":{
"p":0.8402818555,
"r":0.8507728894,
"f":0.8454948301
},
"PERSON":{
"p":0.8898495037,
"r":0.9069843342,
"f":0.898335219
},
"NORP":{
"p":0.902676399,
"r":0.8904,
"f":0.896496174
},
"LOC":{
"p":0.7042253521,
"r":0.6369426752,
"f":0.6688963211
},
"TIME":{
"p":0.7459807074,
"r":0.6783625731,
"f":0.7105666156
},
"WORK_OF_ART":{
"p":0.5303030303,
"r":0.3608247423,
"f":0.4294478528
},
"EVENT":{
"p":0.6593406593,
"r":0.3448275862,
"f":0.4528301887
},
"LAW":{
"p":0.6481481481,
"r":0.546875,
"f":0.593220339
},
"MONEY":{
"p":0.9265944645,
"r":0.9090909091,
"f":0.9177592372
},
"PERCENT":{
"p":0.9072,
"r":0.8683001531,
"f":0.8873239437
},
"PRODUCT":{
"p":0.6506024096,
"r":0.2559241706,
"f":0.3673469388
},
"LANGUAGE":{
"p":0.76,
"r":0.59375,
"f":0.6666666667
}
},
"speed":9753.3917239012
},
"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":"Explosion Vectors (OSCAR 2109 + Wikipedia + OpenSubtitles + WMT News Crawl)",
"url":"https://github.com/explosion/spacy-vectors-builder",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}