|
{ |
|
"lang":"en", |
|
"name":"core_web_md", |
|
"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":300, |
|
"vectors":20000, |
|
"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":0.9730543186, |
|
"sents_p":0.9196707931, |
|
"sents_r":0.891945379, |
|
"sents_f":0.9055959278, |
|
"dep_uas":0.9190946961, |
|
"dep_las":0.9007569337, |
|
"dep_las_per_type":{ |
|
"prep":{ |
|
"p":0.8560125989, |
|
"r":0.8662113451, |
|
"f":0.8610817743 |
|
}, |
|
"det":{ |
|
"p":0.9772801303, |
|
"r":0.978634918, |
|
"f":0.977957055 |
|
}, |
|
"pobj":{ |
|
"p":0.962675204, |
|
"r":0.9682701747, |
|
"f":0.9654645836 |
|
}, |
|
"nsubj":{ |
|
"p":0.9572204318, |
|
"r":0.9499233297, |
|
"f":0.9535579207 |
|
}, |
|
"aux":{ |
|
"p":0.9785175322, |
|
"r":0.9813050832, |
|
"f":0.9799093253 |
|
}, |
|
"advmod":{ |
|
"p":0.8565884933, |
|
"r":0.854282349, |
|
"f":0.8554338669 |
|
}, |
|
"relcl":{ |
|
"p":0.767698328, |
|
"r":0.7830188679, |
|
"f":0.7752829172 |
|
}, |
|
"root":{ |
|
"p":0.919640425, |
|
"r":0.890823933, |
|
"f":0.9050028482 |
|
}, |
|
"xcomp":{ |
|
"p":0.8803810868, |
|
"r":0.8955491744, |
|
"f":0.8879003559 |
|
}, |
|
"amod":{ |
|
"p":0.9190016943, |
|
"r":0.9137026239, |
|
"f":0.9163444982 |
|
}, |
|
"compound":{ |
|
"p":0.9179876706, |
|
"r":0.9288260192, |
|
"f":0.9233750415 |
|
}, |
|
"poss":{ |
|
"p":0.96996997, |
|
"r":0.9752415459, |
|
"f":0.9725986149 |
|
}, |
|
"ccomp":{ |
|
"p":0.7815332326, |
|
"r":0.8429735234, |
|
"f":0.8110915148 |
|
}, |
|
"attr":{ |
|
"p":0.9055374593, |
|
"r":0.9352396972, |
|
"f":0.920148945 |
|
}, |
|
"case":{ |
|
"p":0.9772502473, |
|
"r":0.988988989, |
|
"f":0.9830845771 |
|
}, |
|
"mark":{ |
|
"p":0.9047619048, |
|
"r":0.9112347642, |
|
"f":0.9079867987 |
|
}, |
|
"intj":{ |
|
"p":0.671630094, |
|
"r":0.6278388278, |
|
"f":0.6489965922 |
|
}, |
|
"advcl":{ |
|
"p":0.6692111959, |
|
"r":0.6623016872, |
|
"f":0.6657385141 |
|
}, |
|
"cc":{ |
|
"p":0.8336738373, |
|
"r":0.8296854443, |
|
"f":0.8316748591 |
|
}, |
|
"neg":{ |
|
"p":0.944027986, |
|
"r":0.9478173608, |
|
"f":0.9459188783 |
|
}, |
|
"conj":{ |
|
"p":0.7673786887, |
|
"r":0.7823514602, |
|
"f":0.7747927445 |
|
}, |
|
"nsubjpass":{ |
|
"p":0.9214175655, |
|
"r":0.92, |
|
"f":0.9207082371 |
|
}, |
|
"auxpass":{ |
|
"p":0.9504242966, |
|
"r":0.969476082, |
|
"f":0.9598556608 |
|
}, |
|
"dobj":{ |
|
"p":0.9276569005, |
|
"r":0.9411108455, |
|
"f":0.934335443 |
|
}, |
|
"nummod":{ |
|
"p":0.9344345616, |
|
"r":0.9285353535, |
|
"f":0.9314756175 |
|
}, |
|
"npadvmod":{ |
|
"p":0.7719101124, |
|
"r":0.7321492007, |
|
"f":0.7515041021 |
|
}, |
|
"prt":{ |
|
"p":0.8105436573, |
|
"r":0.8817204301, |
|
"f":0.8446351931 |
|
}, |
|
"pcomp":{ |
|
"p":0.8834399431, |
|
"r":0.8704481793, |
|
"f":0.8768959436 |
|
}, |
|
"expl":{ |
|
"p":0.978858351, |
|
"r":0.9914346895, |
|
"f":0.985106383 |
|
}, |
|
"acl":{ |
|
"p":0.7338709677, |
|
"r":0.695035461, |
|
"f":0.7139254693 |
|
}, |
|
"agent":{ |
|
"p":0.8931034483, |
|
"r":0.9283154122, |
|
"f":0.9103690685 |
|
}, |
|
"dative":{ |
|
"p":0.7809278351, |
|
"r":0.6949541284, |
|
"f":0.7354368932 |
|
}, |
|
"acomp":{ |
|
"p":0.9010440309, |
|
"r":0.9002267574, |
|
"f":0.9006352087 |
|
}, |
|
"dep":{ |
|
"p":0.4375, |
|
"r":0.1818181818, |
|
"f":0.2568807339 |
|
}, |
|
"csubj":{ |
|
"p":0.6994535519, |
|
"r":0.7573964497, |
|
"f":0.7272727273 |
|
}, |
|
"quantmod":{ |
|
"p":0.8572710952, |
|
"r":0.775792039, |
|
"f":0.8144989339 |
|
}, |
|
"nmod":{ |
|
"p":0.7576923077, |
|
"r":0.6002437538, |
|
"f":0.6698401904 |
|
}, |
|
"appos":{ |
|
"p":0.7131675875, |
|
"r":0.6720173536, |
|
"f":0.6919812374 |
|
}, |
|
"predet":{ |
|
"p":0.8259109312, |
|
"r":0.8755364807, |
|
"f":0.85 |
|
}, |
|
"preconj":{ |
|
"p":0.5376344086, |
|
"r":0.5813953488, |
|
"f":0.5586592179 |
|
}, |
|
"oprd":{ |
|
"p":0.8384879725, |
|
"r":0.728358209, |
|
"f":0.7795527157 |
|
}, |
|
"parataxis":{ |
|
"p":0.627027027, |
|
"r":0.5032537961, |
|
"f":0.5583634176 |
|
}, |
|
"meta":{ |
|
"p":0.9047619048, |
|
"r":0.3653846154, |
|
"f":0.5205479452 |
|
}, |
|
"csubjpass":{ |
|
"p":0.625, |
|
"r":0.8333333333, |
|
"f":0.7142857143 |
|
} |
|
}, |
|
"ents_p":0.8511198946, |
|
"ents_r":0.8411458333, |
|
"ents_f":0.8461034709, |
|
"ents_per_type":{ |
|
"DATE":{ |
|
"p":0.8734459675, |
|
"r":0.8698412698, |
|
"f":0.8716398918 |
|
}, |
|
"GPE":{ |
|
"p":0.9166902805, |
|
"r":0.9023709902, |
|
"f":0.9094742761 |
|
}, |
|
"ORDINAL":{ |
|
"p":0.7703081232, |
|
"r":0.8540372671, |
|
"f":0.8100147275 |
|
}, |
|
"ORG":{ |
|
"p":0.8110611273, |
|
"r":0.8125662778, |
|
"f":0.8118130049 |
|
}, |
|
"CARDINAL":{ |
|
"p":0.8257619321, |
|
"r":0.853745541, |
|
"f":0.839520608 |
|
}, |
|
"PERSON":{ |
|
"p":0.8546404425, |
|
"r":0.9076370757, |
|
"f":0.8803418803 |
|
}, |
|
"NORP":{ |
|
"p":0.9006410256, |
|
"r":0.8992, |
|
"f":0.8999199359 |
|
}, |
|
"LOC":{ |
|
"p":0.7007575758, |
|
"r":0.5891719745, |
|
"f":0.6401384083 |
|
}, |
|
"LAW":{ |
|
"p":0.5, |
|
"r":0.4375, |
|
"f":0.4666666667 |
|
}, |
|
"FAC":{ |
|
"p":0.4519230769, |
|
"r":0.3615384615, |
|
"f":0.4017094017 |
|
}, |
|
"TIME":{ |
|
"p":0.752293578, |
|
"r":0.7192982456, |
|
"f":0.735426009 |
|
}, |
|
"QUANTITY":{ |
|
"p":0.7867647059, |
|
"r":0.5879120879, |
|
"f":0.6729559748 |
|
}, |
|
"WORK_OF_ART":{ |
|
"p":0.5416666667, |
|
"r":0.3350515464, |
|
"f":0.4140127389 |
|
}, |
|
"MONEY":{ |
|
"p":0.9107142857, |
|
"r":0.9031877214, |
|
"f":0.9069353883 |
|
}, |
|
"EVENT":{ |
|
"p":0.5578947368, |
|
"r":0.3045977011, |
|
"f":0.3940520446 |
|
}, |
|
"PERCENT":{ |
|
"p":0.9216, |
|
"r":0.8820826953, |
|
"f":0.9014084507 |
|
}, |
|
"PRODUCT":{ |
|
"p":0.48, |
|
"r":0.2274881517, |
|
"f":0.308681672 |
|
}, |
|
"LANGUAGE":{ |
|
"p":0.8333333333, |
|
"r":0.625, |
|
"f":0.7142857143 |
|
} |
|
}, |
|
"speed":8543.7326288502 |
|
}, |
|
"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":[ |
|
|
|
] |
|
} |