en_core_web_lg / meta.json
adrianeboyd's picture
Update spaCy pipeline
25fc841
raw history blame
No virus
10.3 kB
{
"lang":"en",
"name":"core_web_lg",
"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":514157,
"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":0.9734404547,
"sents_p":0.9179347826,
"sents_r":0.8913516723,
"sents_f":0.90444794,
"dep_uas":0.9204363007,
"dep_las":0.9023174614,
"dep_las_per_type":{
"prep":{
"p":0.8597877625,
"r":0.8669322709,
"f":0.8633452361
},
"det":{
"p":0.9797074284,
"r":0.9803066134,
"f":0.9800069293
},
"pobj":{
"p":0.963921354,
"r":0.9683879835,
"f":0.9661495063
},
"nsubj":{
"p":0.9573359244,
"r":0.94966046,
"f":0.9534827457
},
"aux":{
"p":0.981595092,
"r":0.9828184813,
"f":0.9822064057
},
"advmod":{
"p":0.8567202029,
"r":0.8526838297,
"f":0.8546972508
},
"relcl":{
"p":0.7682926829,
"r":0.7772133527,
"f":0.7727272727
},
"root":{
"p":0.9196058444,
"r":0.8926710205,
"f":0.9059382741
},
"xcomp":{
"p":0.8853797019,
"r":0.8955491744,
"f":0.8904354033
},
"amod":{
"p":0.9199114468,
"r":0.9153223194,
"f":0.9176111454
},
"compound":{
"p":0.9198242724,
"r":0.9328358209,
"f":0.9262843555
},
"poss":{
"p":0.9735205617,
"r":0.9768518519,
"f":0.9751833618
},
"ccomp":{
"p":0.7757201646,
"r":0.8446028513,
"f":0.8086973479
},
"attr":{
"p":0.9064542484,
"r":0.93313709,
"f":0.919602155
},
"case":{
"p":0.9797330697,
"r":0.991991992,
"f":0.9858244218
},
"mark":{
"p":0.9015625,
"r":0.9173290938,
"f":0.9093774626
},
"intj":{
"p":0.680533752,
"r":0.6351648352,
"f":0.6570670709
},
"advcl":{
"p":0.6686002522,
"r":0.6675900277,
"f":0.6680947581
},
"cc":{
"p":0.8381204182,
"r":0.8341107523,
"f":0.8361107781
},
"neg":{
"p":0.9451371571,
"r":0.9508278976,
"f":0.947973987
},
"conj":{
"p":0.7760468594,
"r":0.7838620342,
"f":0.7799348697
},
"nsubjpass":{
"p":0.9234693878,
"r":0.9282051282,
"f":0.925831202
},
"auxpass":{
"p":0.9468791501,
"r":0.9744874715,
"f":0.9604849573
},
"dobj":{
"p":0.9278213166,
"r":0.9434217866,
"f":0.9355565214
},
"nummod":{
"p":0.9377224199,
"r":0.9315656566,
"f":0.9346338992
},
"npadvmod":{
"p":0.7837218189,
"r":0.7285968028,
"f":0.7551546392
},
"prt":{
"p":0.8103025348,
"r":0.8879928315,
"f":0.8473706712
},
"pcomp":{
"p":0.8873937677,
"r":0.8774509804,
"f":0.8823943662
},
"expl":{
"p":0.9809725159,
"r":0.9935760171,
"f":0.9872340426
},
"acl":{
"p":0.7534883721,
"r":0.7070376432,
"f":0.7295243456
},
"agent":{
"p":0.9042735043,
"r":0.9480286738,
"f":0.9256342957
},
"dative":{
"p":0.7725,
"r":0.7087155963,
"f":0.7392344498
},
"acomp":{
"p":0.9080091533,
"r":0.8997732426,
"f":0.9038724374
},
"dep":{
"p":0.3263473054,
"r":0.1769480519,
"f":0.2294736842
},
"csubj":{
"p":0.7045454545,
"r":0.7337278107,
"f":0.7188405797
},
"quantmod":{
"p":0.8531468531,
"r":0.7928513404,
"f":0.8218947368
},
"nmod":{
"p":0.7539432177,
"r":0.5825716027,
"f":0.6572705397
},
"appos":{
"p":0.6997270246,
"r":0.6672451193,
"f":0.6831001555
},
"predet":{
"p":0.8524590164,
"r":0.8927038627,
"f":0.8721174004
},
"preconj":{
"p":0.5684210526,
"r":0.6279069767,
"f":0.5966850829
},
"oprd":{
"p":0.8322368421,
"r":0.7552238806,
"f":0.7918622848
},
"parataxis":{
"p":0.6323119777,
"r":0.4924078091,
"f":0.5536585366
},
"meta":{
"p":0.8461538462,
"r":0.4230769231,
"f":0.5641025641
},
"csubjpass":{
"p":0.4285714286,
"r":0.5,
"f":0.4615384615
}
},
"ents_p":0.8636641533,
"ents_r":0.8489583333,
"ents_f":0.8562481059,
"ents_per_type":{
"DATE":{
"p":0.8711209626,
"r":0.8733333333,
"f":0.8722257451
},
"GPE":{
"p":0.9365811473,
"r":0.9062761506,
"f":0.9211794726
},
"ORDINAL":{
"p":0.787965616,
"r":0.8540372671,
"f":0.8196721311
},
"FAC":{
"p":0.4910714286,
"r":0.4230769231,
"f":0.4545454545
},
"ORG":{
"p":0.8242392445,
"r":0.8329798515,
"f":0.8285864979
},
"QUANTITY":{
"p":0.8231292517,
"r":0.6648351648,
"f":0.73556231
},
"LOC":{
"p":0.7222222222,
"r":0.6624203822,
"f":0.6910299003
},
"CARDINAL":{
"p":0.8295912493,
"r":0.8567181926,
"f":0.8429365311
},
"PERSON":{
"p":0.8915049316,
"r":0.9144908616,
"f":0.9028516191
},
"NORP":{
"p":0.9150485437,
"r":0.9048,
"f":0.9098954143
},
"TIME":{
"p":0.7133956386,
"r":0.6695906433,
"f":0.6907993967
},
"WORK_OF_ART":{
"p":0.544,
"r":0.3505154639,
"f":0.4263322884
},
"EVENT":{
"p":0.606741573,
"r":0.3103448276,
"f":0.4106463878
},
"LAW":{
"p":0.3870967742,
"r":0.375,
"f":0.380952381
},
"MONEY":{
"p":0.9183673469,
"r":0.9031877214,
"f":0.9107142857
},
"PERCENT":{
"p":0.9079365079,
"r":0.875957121,
"f":0.8916601715
},
"LANGUAGE":{
"p":0.6296296296,
"r":0.53125,
"f":0.5762711864
},
"PRODUCT":{
"p":0.5333333333,
"r":0.2274881517,
"f":0.3189368771
}
},
"speed":7875.967150799
},
"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":[
]
}