en_core_web_sm / meta.json
osanseviero's picture
Update spaCy pipeline
f35dec9
raw
history blame
10 kB
{
"lang":"en",
"name":"core_web_sm",
"version":"3.1.0",
"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":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"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,
"tag_acc":0.9720712187,
"dep_uas":0.9185392711,
"dep_las":0.9001546872,
"ents_p":0.8424355924,
"ents_r":0.8335336538,
"ents_f":0.8379609817,
"sents_p":0.9074955788,
"sents_r":0.8801372122,
"sents_f":0.893607046,
"speed":10426.0619939972,
"dep_las_per_type":{
"prep":{
"p":0.8554402587,
"r":0.8633276418,
"f":0.8593658527
},
"det":{
"p":0.9772329247,
"r":0.9783087336,
"f":0.9777705332
},
"pobj":{
"p":0.9603285837,
"r":0.9686628706,
"f":0.9644777228
},
"nsubj":{
"p":0.9598718747,
"r":0.945279299,
"f":0.9525197007
},
"aux":{
"p":0.9795737123,
"r":0.9819282471,
"f":0.9807495665
},
"advmod":{
"p":0.8538267452,
"r":0.8541140838,
"f":0.8539703903
},
"relcl":{
"p":0.764978602,
"r":0.7783018868,
"f":0.7715827338
},
"root":{
"p":0.9199754818,
"r":0.8910878026,
"f":0.9053012533
},
"xcomp":{
"p":0.8813440672,
"r":0.903804738,
"f":0.892433103
},
"amod":{
"p":0.9171875,
"r":0.9127308066,
"f":0.9149537263
},
"compound":{
"p":0.916057391,
"r":0.9280463355,
"f":0.9220128918
},
"poss":{
"p":0.9744672296,
"r":0.9756441224,
"f":0.9750553209
},
"ccomp":{
"p":0.7747747748,
"r":0.8407331976,
"f":0.8064075015
},
"attr":{
"p":0.8989490703,
"r":0.9352396972,
"f":0.9167353669
},
"case":{
"p":0.9801980198,
"r":0.990990991,
"f":0.9855649577
},
"mark":{
"p":0.9015392781,
"r":0.9001059883,
"f":0.9008220631
},
"intj":{
"p":0.6712856043,
"r":0.6388278388,
"f":0.6546546547
},
"advcl":{
"p":0.6687116564,
"r":0.6587761269,
"f":0.6637067106
},
"cc":{
"p":0.8426682692,
"r":0.8385360603,
"f":0.8405970865
},
"neg":{
"p":0.9461346633,
"r":0.9518314099,
"f":0.9489744872
},
"conj":{
"p":0.7715100422,
"r":0.7833585096,
"f":0.7773891318
},
"nsubjpass":{
"p":0.9296875,
"r":0.9153846154,
"f":0.9224806202
},
"auxpass":{
"p":0.9496883348,
"r":0.9717539863,
"f":0.9605944607
},
"dobj":{
"p":0.919667805,
"r":0.9442186628,
"f":0.9317815437
},
"nummod":{
"p":0.9341637011,
"r":0.928030303,
"f":0.9310869014
},
"npadvmod":{
"p":0.7723823976,
"r":0.723268206,
"f":0.7470188956
},
"prt":{
"p":0.8175842235,
"r":0.8915770609,
"f":0.852978997
},
"pcomp":{
"p":0.890625,
"r":0.8781512605,
"f":0.8843441467
},
"expl":{
"p":0.978858351,
"r":0.9914346895,
"f":0.985106383
},
"acl":{
"p":0.7473745624,
"r":0.6988543372,
"f":0.7223005357
},
"agent":{
"p":0.8937605396,
"r":0.9498207885,
"f":0.9209383145
},
"dative":{
"p":0.7608695652,
"r":0.7224770642,
"f":0.7411764706
},
"acomp":{
"p":0.91184573,
"r":0.9006802721,
"f":0.9062286105
},
"dep":{
"p":0.3689655172,
"r":0.1737012987,
"f":0.2362030905
},
"csubj":{
"p":0.6424242424,
"r":0.6272189349,
"f":0.6347305389
},
"quantmod":{
"p":0.8624667258,
"r":0.7896019496,
"f":0.8244274809
},
"nmod":{
"p":0.7359073359,
"r":0.5807434491,
"f":0.6491825613
},
"appos":{
"p":0.7011441648,
"r":0.6646420824,
"f":0.6824053452
},
"predet":{
"p":0.8514056225,
"r":0.9098712446,
"f":0.8796680498
},
"preconj":{
"p":0.476635514,
"r":0.5930232558,
"f":0.5284974093
},
"oprd":{
"p":0.8193979933,
"r":0.7313432836,
"f":0.7728706625
},
"parataxis":{
"p":0.6336088154,
"r":0.4989154013,
"f":0.5582524272
},
"meta":{
"p":0.7727272727,
"r":0.3269230769,
"f":0.4594594595
},
"csubjpass":{
"p":0.5,
"r":0.8333333333,
"f":0.625
}
},
"ents_per_type":{
"DATE":{
"p":0.8659955961,
"r":0.873968254,
"f":0.8699636593
},
"GPE":{
"p":0.9142529395,
"r":0.8892608089,
"f":0.9015837104
},
"ORG":{
"p":0.789707419,
"r":0.8014316013,
"f":0.7955263158
},
"FAC":{
"p":0.3679245283,
"r":0.3,
"f":0.3305084746
},
"CARDINAL":{
"p":0.8146892655,
"r":0.8573127229,
"f":0.8354577057
},
"PERSON":{
"p":0.8424487259,
"r":0.8847911227,
"f":0.8631009233
},
"NORP":{
"p":0.9078415521,
"r":0.8984,
"f":0.9030960997
},
"ORDINAL":{
"p":0.7787114846,
"r":0.8633540373,
"f":0.8188512518
},
"LOC":{
"p":0.713740458,
"r":0.5955414013,
"f":0.6493055556
},
"TIME":{
"p":0.712962963,
"r":0.6754385965,
"f":0.6936936937
},
"PRODUCT":{
"p":0.5510204082,
"r":0.2559241706,
"f":0.3495145631
},
"QUANTITY":{
"p":0.842519685,
"r":0.5879120879,
"f":0.6925566343
},
"WORK_OF_ART":{
"p":0.46875,
"r":0.3092783505,
"f":0.3726708075
},
"EVENT":{
"p":0.595959596,
"r":0.3390804598,
"f":0.4322344322
},
"MONEY":{
"p":0.9182692308,
"r":0.9020070838,
"f":0.9100655152
},
"LAW":{
"p":0.5555555556,
"r":0.46875,
"f":0.5084745763
},
"PERCENT":{
"p":0.92,
"r":0.8805513017,
"f":0.8998435055
},
"LANGUAGE":{
"p":0.7692307692,
"r":0.625,
"f":0.6896551724
}
}
},
"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"
}
],
"requirements":[
]
}