en_core_web_md / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
1d33edc
raw history blame
No virus
10.4 kB
{
"lang":"en",
"name":"core_web_md",
"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":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"
],
"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":0.9736958159,
"sents_p":0.9144345238,
"sents_r":0.8918134442,
"sents_f":0.9029823331,
"dep_uas":0.9186827918,
"dep_las":0.9006556195,
"dep_las_per_type":{
"prep":{
"p":0.8569122175,
"r":0.8659836843,
"f":0.8614240691
},
"det":{
"p":0.9770765472,
"r":0.9784310528,
"f":0.9777533309
},
"pobj":{
"p":0.9611128429,
"r":0.968623601,
"f":0.9648536056
},
"nsubj":{
"p":0.9594312375,
"r":0.9459802848,
"f":0.9526582837
},
"aux":{
"p":0.9797621161,
"r":0.9826404344,
"f":0.9811991644
},
"advmod":{
"p":0.8561672709,
"r":0.8543664816,
"f":0.8552659283
},
"relcl":{
"p":0.765480427,
"r":0.780478955,
"f":0.772906935
},
"root":{
"p":0.9166215118,
"r":0.8927369879,
"f":0.9045216055
},
"xcomp":{
"p":0.8828097423,
"r":0.8977027997,
"f":0.8901939847
},
"amod":{
"p":0.92090506,
"r":0.9149983803,
"f":0.9179422183
},
"compound":{
"p":0.917950968,
"r":0.9321118289,
"f":0.924977203
},
"poss":{
"p":0.9744877461,
"r":0.9764492754,
"f":0.9754675246
},
"ccomp":{
"p":0.7754030746,
"r":0.8423625255,
"f":0.8074970715
},
"attr":{
"p":0.8974979822,
"r":0.9352396972,
"f":0.9159802306
},
"case":{
"p":0.9811881188,
"r":0.991991992,
"f":0.9865604778
},
"mark":{
"p":0.9043686734,
"r":0.8995760466,
"f":0.9019659936
},
"intj":{
"p":0.6650717703,
"r":0.610989011,
"f":0.636884307
},
"advcl":{
"p":0.6723033564,
"r":0.6607907328,
"f":0.666497333
},
"cc":{
"p":0.835978836,
"r":0.8314794881,
"f":0.8337230917
},
"neg":{
"p":0.9431988042,
"r":0.9498243853,
"f":0.9465
},
"conj":{
"p":0.7615497433,
"r":0.7843655589,
"f":0.7727892844
},
"nsubjpass":{
"p":0.9269311065,
"r":0.9107692308,
"f":0.9187790998
},
"auxpass":{
"p":0.9508050089,
"r":0.9685649203,
"f":0.9596027985
},
"dobj":{
"p":0.9220839813,
"r":0.9449358515,
"f":0.9333700657
},
"nummod":{
"p":0.9399338254,
"r":0.9325757576,
"f":0.9362403346
},
"npadvmod":{
"p":0.7793445122,
"r":0.7264653641,
"f":0.7519764663
},
"prt":{
"p":0.8145094806,
"r":0.8853046595,
"f":0.8484328038
},
"pcomp":{
"p":0.8889679715,
"r":0.8746498599,
"f":0.8817507942
},
"expl":{
"p":0.983014862,
"r":0.9914346895,
"f":0.987206823
},
"acl":{
"p":0.7449741528,
"r":0.7075831969,
"f":0.7257974259
},
"agent":{
"p":0.8957264957,
"r":0.9390681004,
"f":0.9168853893
},
"dative":{
"p":0.7732997481,
"r":0.7041284404,
"f":0.7370948379
},
"acomp":{
"p":0.9094236048,
"r":0.9015873016,
"f":0.9054884992
},
"dep":{
"p":0.3909465021,
"r":0.1542207792,
"f":0.2211874272
},
"csubj":{
"p":0.8098591549,
"r":0.6804733728,
"f":0.7395498392
},
"quantmod":{
"p":0.8739800544,
"r":0.7831031682,
"f":0.8260497001
},
"nmod":{
"p":0.7614457831,
"r":0.5776965265,
"f":0.656964657
},
"appos":{
"p":0.6850678733,
"r":0.6568329718,
"f":0.6706533776
},
"predet":{
"p":0.8467741935,
"r":0.9012875536,
"f":0.8731808732
},
"preconj":{
"p":0.5454545455,
"r":0.6279069767,
"f":0.5837837838
},
"oprd":{
"p":0.8413793103,
"r":0.728358209,
"f":0.7808
},
"parataxis":{
"p":0.6129943503,
"r":0.4707158351,
"f":0.5325153374
},
"meta":{
"p":0.8,
"r":0.3076923077,
"f":0.4444444444
},
"csubjpass":{
"p":0.5714285714,
"r":0.6666666667,
"f":0.6153846154
}
},
"ents_p":0.8531330602,
"ents_r":0.8448016827,
"ents_f":0.8489469314,
"ents_per_type":{
"DATE":{
"p":0.8645998102,
"r":0.8676190476,
"f":0.8661067977
},
"GPE":{
"p":0.9183846371,
"r":0.9071129707,
"f":0.9127140051
},
"ORDINAL":{
"p":0.7765363128,
"r":0.8633540373,
"f":0.8176470588
},
"PERSON":{
"p":0.8805737449,
"r":0.9216710183,
"f":0.9006538032
},
"ORG":{
"p":0.8025329543,
"r":0.8231707317,
"f":0.8127208481
},
"QUANTITY":{
"p":0.7697841727,
"r":0.5879120879,
"f":0.6666666667
},
"CARDINAL":{
"p":0.8279202279,
"r":0.8638525565,
"f":0.8455048007
},
"NORP":{
"p":0.9102667745,
"r":0.9008,
"f":0.905508645
},
"LOC":{
"p":0.7022058824,
"r":0.6082802548,
"f":0.6518771331
},
"FAC":{
"p":0.4122807018,
"r":0.3615384615,
"f":0.3852459016
},
"TIME":{
"p":0.7450980392,
"r":0.6666666667,
"f":0.7037037037
},
"PRODUCT":{
"p":0.6376811594,
"r":0.2085308057,
"f":0.3142857143
},
"MONEY":{
"p":0.9027611044,
"r":0.8878394333,
"f":0.8952380952
},
"EVENT":{
"p":0.6043956044,
"r":0.316091954,
"f":0.4150943396
},
"WORK_OF_ART":{
"p":0.5317460317,
"r":0.3453608247,
"f":0.41875
},
"LAW":{
"p":0.4666666667,
"r":0.328125,
"f":0.3853211009
},
"PERCENT":{
"p":0.9090909091,
"r":0.8728943338,
"f":0.890625
},
"LANGUAGE":{
"p":0.6956521739,
"r":0.5,
"f":0.5818181818
}
},
"speed":7620.1455610511
},
"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":[
]
}