ktcole's picture
Update spaCy pipeline
185d3d9 verified
raw
history blame
10.2 kB
{
"lang":"en",
"name":"pakistan_caselaw_ner",
"version":"3.8.0",
"description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Kevin Cole",
"email":"me@kevin-cole.com",
"url":"https://kevin-cole.com",
"license":"MIT",
"spacy_version":">=3.8.0,<3.9.0",
"spacy_git_version":"5010fcbd3",
"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",
"_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",
"CASE_NUMBER",
"DATE",
"EVENT",
"FAC",
"GPE",
"LANGUAGE",
"LAW",
"LOC",
"MONEY",
"NORP",
"ORDINAL",
"ORG",
"PERCENT",
"PERSON",
"PETITIONER",
"PRODUCT",
"QUANTITY",
"RESPONDENT",
"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":0.972937262,
"sents_p":0.9200841934,
"sents_r":0.8939244013,
"sents_f":0.9068156724,
"dep_uas":0.9176955214,
"dep_las":0.8991533598,
"dep_las_per_type":{
"prep":{
"p":0.8541604085,
"r":0.8631379245,
"f":0.8586257006
},
"det":{
"p":0.9768729642,
"r":0.9782271875,
"f":0.9775496068
},
"pobj":{
"p":0.9620664033,
"r":0.966071078,
"f":0.9640645819
},
"nsubj":{
"p":0.9573684677,
"r":0.9454983571,
"f":0.9513963894
},
"aux":{
"p":0.9792295402,
"r":0.982106294,
"f":0.9806658074
},
"advmod":{
"p":0.8525198045,
"r":0.8510853104,
"f":0.8518019535
},
"relcl":{
"p":0.7660107335,
"r":0.776850508,
"f":0.7713925419
},
"root":{
"p":0.9179682195,
"r":0.8917474767,
"f":0.9046678936
},
"xcomp":{
"p":0.8814035088,
"r":0.9016511127,
"f":0.8914123492
},
"amod":{
"p":0.9161996611,
"r":0.9109167477,
"f":0.9135505669
},
"compound":{
"p":0.916113822,
"r":0.9305524616,
"f":0.9232766957
},
"poss":{
"p":0.9741586538,
"r":0.9788647343,
"f":0.9765060241
},
"ccomp":{
"p":0.7786216062,
"r":0.8352342159,
"f":0.8059349514
},
"attr":{
"p":0.8972491909,
"r":0.9327165685,
"f":0.9146391753
},
"case":{
"p":0.9782608696,
"r":0.990990991,
"f":0.9845847837
},
"mark":{
"p":0.9028511088,
"r":0.906200318,
"f":0.9045226131
},
"intj":{
"p":0.6679841897,
"r":0.619047619,
"f":0.6425855513
},
"advcl":{
"p":0.6656519533,
"r":0.6607907328,
"f":0.6632124352
},
"cc":{
"p":0.8345964153,
"r":0.8298050472,
"f":0.8321938347
},
"neg":{
"p":0.9475786321,
"r":0.9523331661,
"f":0.9499499499
},
"conj":{
"p":0.7649689441,
"r":0.7751762336,
"f":0.7700387645
},
"nsubjpass":{
"p":0.9159021407,
"r":0.9215384615,
"f":0.9187116564
},
"auxpass":{
"p":0.9494232476,
"r":0.9749430524,
"f":0.9620139357
},
"dobj":{
"p":0.9231431478,
"r":0.9399155311,
"f":0.9314538419
},
"nummod":{
"p":0.9353284301,
"r":0.9313131313,
"f":0.9333164621
},
"npadvmod":{
"p":0.7748267898,
"r":0.7150976909,
"f":0.7437650102
},
"prt":{
"p":0.8148760331,
"r":0.8835125448,
"f":0.8478073947
},
"pcomp":{
"p":0.8693820225,
"r":0.8669467787,
"f":0.8681626928
},
"expl":{
"p":0.9789029536,
"r":0.9935760171,
"f":0.9861849097
},
"acl":{
"p":0.7417295415,
"r":0.6972176759,
"f":0.7187851519
},
"agent":{
"p":0.8994889267,
"r":0.9462365591,
"f":0.9222707424
},
"dative":{
"p":0.7669172932,
"r":0.7018348624,
"f":0.7329341317
},
"acomp":{
"p":0.9132441163,
"r":0.8975056689,
"f":0.9053064959
},
"dep":{
"p":0.3686006826,
"r":0.1753246753,
"f":0.2376237624
},
"csubj":{
"p":0.7039106145,
"r":0.7455621302,
"f":0.724137931
},
"quantmod":{
"p":0.8625336927,
"r":0.7798537774,
"f":0.819112628
},
"nmod":{
"p":0.752886836,
"r":0.5959780622,
"f":0.6653061224
},
"appos":{
"p":0.6866606983,
"r":0.6655097614,
"f":0.6759198061
},
"predet":{
"p":0.8406374502,
"r":0.9055793991,
"f":0.8719008264
},
"preconj":{
"p":0.5591397849,
"r":0.6046511628,
"f":0.5810055866
},
"oprd":{
"p":0.8287671233,
"r":0.7223880597,
"f":0.7719298246
},
"parataxis":{
"p":0.5860215054,
"r":0.4728850325,
"f":0.5234093637
},
"meta":{
"p":0.8,
"r":0.4615384615,
"f":0.5853658537
},
"csubjpass":{
"p":0.625,
"r":0.8333333333,
"f":0.7142857143
}
},
"ents_p":0.8429743795,
"ents_r":0.8436498397,
"ents_f":0.8433119744,
"ents_per_type":{
"DATE":{
"p":0.8531038722,
"r":0.8812698413,
"f":0.8669581512
},
"GPE":{
"p":0.9142205757,
"r":0.8948396095,
"f":0.9044262757
},
"ORDINAL":{
"p":0.7741046832,
"r":0.8726708075,
"f":0.8204379562
},
"ORG":{
"p":0.7904834996,
"r":0.8191940615,
"f":0.8045827366
},
"CARDINAL":{
"p":0.8149386845,
"r":0.8692033294,
"f":0.8411967779
},
"FAC":{
"p":0.3904761905,
"r":0.3153846154,
"f":0.3489361702
},
"PERSON":{
"p":0.8574969021,
"r":0.9033942559,
"f":0.8798474253
},
"NORP":{
"p":0.903122498,
"r":0.9024,
"f":0.9027611044
},
"TIME":{
"p":0.7454545455,
"r":0.7192982456,
"f":0.7321428571
},
"LOC":{
"p":0.7356321839,
"r":0.6114649682,
"f":0.667826087
},
"MONEY":{
"p":0.915274463,
"r":0.9055489965,
"f":0.9103857567
},
"QUANTITY":{
"p":0.8153846154,
"r":0.5824175824,
"f":0.6794871795
},
"WORK_OF_ART":{
"p":0.4744525547,
"r":0.3350515464,
"f":0.3927492447
},
"EVENT":{
"p":0.6341463415,
"r":0.2988505747,
"f":0.40625
},
"LAW":{
"p":0.4464285714,
"r":0.390625,
"f":0.4166666667
},
"PERCENT":{
"p":0.9153354633,
"r":0.8774885145,
"f":0.8960125098
},
"LANGUAGE":{
"p":0.7692307692,
"r":0.625,
"f":0.6896551724
},
"PRODUCT":{
"p":0.5287356322,
"r":0.2180094787,
"f":0.3087248322
}
},
"speed":9426.1029865937
},
"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":[
"spacy>=3.8.0,<3.9.0"
]
}