en_core_web_md / meta.json
adrianeboyd's picture
Update spaCy pipeline
e283fce
raw
history blame
10.3 kB
{
"lang":"en",
"name":"core_web_md",
"version":"3.5.0",
"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":">=3.5.0,<3.6.0",
"spacy_git_version":"9e0322de1",
"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":0.9986194413,
"token_p":0.9956819193,
"token_r":0.9957659295,
"token_f":0.9957239226,
"tag_acc":0.9732581964,
"sents_p":0.9220717348,
"sents_r":0.8937264991,
"sents_f":0.9076778775,
"dep_uas":0.9205112068,
"dep_las":0.9022890411,
"dep_las_per_type":{
"prep":{
"p":0.8600946728,
"r":0.8686776703,
"f":0.8643648651
},
"det":{
"p":0.9784954995,
"r":0.9795726984,
"f":0.9790338026
},
"pobj":{
"p":0.9627663726,
"r":0.9687021402,
"f":0.9657251356
},
"nsubj":{
"p":0.9581267705,
"r":0.9483461117,
"f":0.9532113526
},
"aux":{
"p":0.9809024694,
"r":0.9830855515,
"f":0.9819927971
},
"advmod":{
"p":0.8600558423,
"r":0.8552078075,
"f":0.8576249736
},
"relcl":{
"p":0.7668209327,
"r":0.7815674891,
"f":0.7741239892
},
"root":{
"p":0.9203949608,
"r":0.8916155419,
"f":0.9057767055
},
"xcomp":{
"p":0.8884574656,
"r":0.9034458004,
"f":0.8958889482
},
"amod":{
"p":0.919493737,
"r":0.9131195335,
"f":0.9162955498
},
"compound":{
"p":0.9178322637,
"r":0.9318890622,
"f":0.9248072512
},
"poss":{
"p":0.9740755627,
"r":0.9756441224,
"f":0.9748592116
},
"ccomp":{
"p":0.7796324081,
"r":0.8466395112,
"f":0.8117555165
},
"attr":{
"p":0.9070904645,
"r":0.9360807401,
"f":0.9213576159
},
"case":{
"p":0.980188212,
"r":0.9904904905,
"f":0.9853124222
},
"mark":{
"p":0.9064065384,
"r":0.9109697933,
"f":0.9086824369
},
"intj":{
"p":0.6742364918,
"r":0.6307692308,
"f":0.6517789553
},
"advcl":{
"p":0.6793032787,
"r":0.6678418534,
"f":0.6735238095
},
"cc":{
"p":0.8407122233,
"r":0.8357851932,
"f":0.8382414682
},
"neg":{
"p":0.9431988042,
"r":0.9498243853,
"f":0.9465
},
"conj":{
"p":0.7720826076,
"r":0.7812185297,
"f":0.7766237017
},
"nsubjpass":{
"p":0.9211997966,
"r":0.9292307692,
"f":0.9251978555
},
"auxpass":{
"p":0.9465311533,
"r":0.9758542141,
"f":0.9609690444
},
"dobj":{
"p":0.9266134085,
"r":0.9427842856,
"f":0.9346289055
},
"nummod":{
"p":0.9384693618,
"r":0.9320707071,
"f":0.9352590903
},
"npadvmod":{
"p":0.7770219199,
"r":0.7303730018,
"f":0.7529756455
},
"prt":{
"p":0.8134206219,
"r":0.8906810036,
"f":0.8502994012
},
"pcomp":{
"p":0.8900785153,
"r":0.8732492997,
"f":0.8815835984
},
"expl":{
"p":0.9809725159,
"r":0.9935760171,
"f":0.9872340426
},
"acl":{
"p":0.7492762015,
"r":0.7059465357,
"f":0.7269662921
},
"agent":{
"p":0.8900169205,
"r":0.9426523297,
"f":0.9155787641
},
"dative":{
"p":0.8016085791,
"r":0.6857798165,
"f":0.739184178
},
"acomp":{
"p":0.9135460009,
"r":0.8961451247,
"f":0.9047619048
},
"dep":{
"p":0.3758389262,
"r":0.1818181818,
"f":0.2450765864
},
"csubj":{
"p":0.7878787879,
"r":0.7692307692,
"f":0.7784431138
},
"quantmod":{
"p":0.8629893238,
"r":0.7879772543,
"f":0.8237791932
},
"nmod":{
"p":0.7400150716,
"r":0.5984156002,
"f":0.6617250674
},
"appos":{
"p":0.702283105,
"r":0.6672451193,
"f":0.6843159066
},
"predet":{
"p":0.84,
"r":0.9012875536,
"f":0.8695652174
},
"preconj":{
"p":0.3617021277,
"r":0.5930232558,
"f":0.449339207
},
"oprd":{
"p":0.8333333333,
"r":0.7462686567,
"f":0.7874015748
},
"parataxis":{
"p":0.6051948052,
"r":0.5054229935,
"f":0.5508274232
},
"meta":{
"p":0.78125,
"r":0.4807692308,
"f":0.5952380952
},
"csubjpass":{
"p":0.5555555556,
"r":0.8333333333,
"f":0.6666666667
}
},
"ents_p":0.8494302632,
"ents_r":0.8549178686,
"ents_f":0.8521652315,
"ents_per_type":{
"DATE":{
"p":0.8584701146,
"r":0.88,
"f":0.8691017401
},
"GPE":{
"p":0.9209341587,
"r":0.9129707113,
"f":0.916935145
},
"ORDINAL":{
"p":0.7768595041,
"r":0.8757763975,
"f":0.8233576642
},
"ORG":{
"p":0.8124188101,
"r":0.8290031813,
"f":0.8206272143
},
"QUANTITY":{
"p":0.8053691275,
"r":0.6593406593,
"f":0.7250755287
},
"CARDINAL":{
"p":0.8215281651,
"r":0.8757431629,
"f":0.8477697842
},
"FAC":{
"p":0.425,
"r":0.3923076923,
"f":0.408
},
"PERSON":{
"p":0.8683001531,
"r":0.9252610966,
"f":0.8958761258
},
"NORP":{
"p":0.8922716628,
"r":0.9144,
"f":0.9032003161
},
"LOC":{
"p":0.7168458781,
"r":0.6369426752,
"f":0.6745362563
},
"TIME":{
"p":0.7065527066,
"r":0.7251461988,
"f":0.7157287157
},
"MONEY":{
"p":0.9112709832,
"r":0.8972845336,
"f":0.9042236764
},
"WORK_OF_ART":{
"p":0.4113475177,
"r":0.2989690722,
"f":0.3462686567
},
"EVENT":{
"p":0.6024096386,
"r":0.2873563218,
"f":0.3891050584
},
"LAW":{
"p":0.5737704918,
"r":0.546875,
"f":0.56
},
"PERCENT":{
"p":0.9020537125,
"r":0.8744257274,
"f":0.8880248834
},
"LANGUAGE":{
"p":0.7083333333,
"r":0.53125,
"f":0.6071428571
},
"PRODUCT":{
"p":0.6363636364,
"r":0.2654028436,
"f":0.3745819398
}
},
"speed":9607.0019342563
},
"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":[
]
}