en_docusco_spacy / meta.json
browndw's picture
Update spaCy pipeline
1118d83 verified
{
"lang":"en",
"name":"docusco_spacy",
"version":"1.5",
"description":"English pipeline for part-of-speech and rhetorical tagging.",
"author":"David Brown",
"email":"dwb2@andrew.cmu.edu",
"url":"https://docuscope.github.io",
"license":"MIT",
"spacy_version":">=3.8.6,<3.9.0",
"spacy_git_version":"911539e",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"tok2vec":[
],
"tagger":[
"APPGE",
"AT",
"AT1",
"BCL21",
"BCL22",
"CC",
"CCB",
"CS",
"CS21",
"CS22",
"CS31",
"CS32",
"CS33",
"CS41",
"CS42",
"CS43",
"CS44",
"CSA",
"CSN",
"CST",
"CSW",
"CSW31",
"CSW32",
"CSW33",
"DA",
"DA1",
"DA2",
"DAR",
"DAT",
"DB",
"DB2",
"DD",
"DD1",
"DD2",
"DDQ",
"DDQGE",
"DDQGE31",
"DDQGE32",
"DDQGE33",
"DDQV",
"DDQV31",
"DDQV32",
"DDQV33",
"EX",
"FO",
"FU",
"FW",
"GE",
"IF",
"II",
"II21",
"II22",
"II31",
"II32",
"II33",
"II41",
"II42",
"II43",
"II44",
"IO",
"IW",
"JJ",
"JJ21",
"JJ22",
"JJ31",
"JJ32",
"JJ33",
"JJ41",
"JJ42",
"JJ43",
"JJ44",
"JJR",
"JJT",
"JK",
"MC",
"MC1",
"MC121",
"MC122",
"MC2",
"MC221",
"MC222",
"MCMC",
"MD",
"MF",
"ND1",
"NN",
"NN1",
"NN121",
"NN122",
"NN131",
"NN132",
"NN133",
"NN141",
"NN142",
"NN143",
"NN144",
"NN2",
"NN21",
"NN22",
"NN221",
"NN222",
"NN31",
"NN32",
"NN33",
"NNA",
"NNB",
"NNL1",
"NNL2",
"NNO",
"NNO2",
"NNT1",
"NNT131",
"NNT132",
"NNT133",
"NNT2",
"NNU",
"NNU1",
"NNU2",
"NNU21",
"NNU22",
"NNU221",
"NNU222",
"NP",
"NP1",
"NP2",
"NPD1",
"NPD2",
"NPM1",
"NPM2",
"PN",
"PN1",
"PN121",
"PN122",
"PN21",
"PN22",
"PNQO",
"PNQS",
"PNQS31",
"PNQS32",
"PNQS33",
"PNQV",
"PNQV31",
"PNQV32",
"PNQV33",
"PNX1",
"PPGE",
"PPH1",
"PPHO1",
"PPHO2",
"PPHS1",
"PPHS2",
"PPIO1",
"PPIO2",
"PPIS1",
"PPIS2",
"PPX1",
"PPX121",
"PPX122",
"PPX2",
"PPX221",
"PPX222",
"PPY",
"RA",
"RA21",
"RA22",
"REX",
"REX21",
"REX22",
"REX41",
"REX42",
"REX43",
"REX44",
"RG",
"RG21",
"RG22",
"RG31",
"RG32",
"RG33",
"RG41",
"RG42",
"RG43",
"RG44",
"RGQ",
"RGQV",
"RGQV31",
"RGQV32",
"RGQV33",
"RGR",
"RGT",
"RL",
"RL21",
"RL22",
"RL31",
"RL32",
"RL33",
"RP",
"RPK",
"RR",
"RR21",
"RR22",
"RR31",
"RR32",
"RR33",
"RR41",
"RR42",
"RR43",
"RR44",
"RR51",
"RR52",
"RR53",
"RR54",
"RR55",
"RRQ",
"RRQV",
"RRQV31",
"RRQV32",
"RRQV33",
"RRR",
"RRT",
"RT",
"RT21",
"RT22",
"RT31",
"RT32",
"RT33",
"RT41",
"RT42",
"RT43",
"RT44",
"TO",
"UH",
"UH21",
"UH22",
"UH31",
"UH32",
"UH33",
"VB0",
"VBDR",
"VBDZ",
"VBG",
"VBI",
"VBM",
"VBN",
"VBR",
"VBZ",
"VD0",
"VDD",
"VDG",
"VDI",
"VDN",
"VDZ",
"VH0",
"VHD",
"VHG",
"VHI",
"VHN",
"VHZ",
"VM",
"VM21",
"VM22",
"VMK",
"VV0",
"VVD",
"VVG",
"VVGK",
"VVI",
"VVN",
"VVNK",
"VVZ",
"XX",
"Y",
"ZZ1",
"ZZ2",
"ZZ221",
"ZZ222"
],
"ner":[
"AcademicTerms",
"AcademicWritingMoves",
"Character",
"Citation",
"CitationAuthority",
"CitationHedged",
"ConfidenceHedged",
"ConfidenceHigh",
"ConfidenceLow",
"Contingent",
"Description",
"Facilitate",
"FirstPerson",
"ForceStressed",
"Future",
"InformationChange",
"InformationChangeNegative",
"InformationChangePositive",
"InformationExposition",
"InformationPlace",
"InformationReportVerbs",
"InformationStates",
"InformationTopics",
"Inquiry",
"Interactive",
"MetadiscourseCohesive",
"MetadiscourseInteractive",
"Narrative",
"Negative",
"Positive",
"PublicTerms",
"Reasoning",
"Responsibility",
"Strategic",
"Uncertainty",
"Updates"
]
},
"pipeline":[
"tok2vec",
"tagger",
"ner"
],
"components":[
"tok2vec",
"tagger",
"ner"
],
"disabled":[
],
"performance":{
"tag_acc":0.9737589551,
"ents_f":0.8085863194,
"ents_p":0.8052588763,
"ents_r":0.8119413755,
"ents_per_type":{
"Narrative":{
"p":0.8069245233,
"r":0.8222163977,
"f":0.8144986922
},
"InformationExposition":{
"p":0.8644792863,
"r":0.8826639923,
"f":0.8734770038
},
"AcademicTerms":{
"p":0.8167635986,
"r":0.845812433,
"f":0.8310342425
},
"ForceStressed":{
"p":0.8082751873,
"r":0.8096379919,
"f":0.8089560156
},
"ConfidenceHedged":{
"p":0.847071524,
"r":0.9061460168,
"f":0.8756135158
},
"InformationReportVerbs":{
"p":0.817106375,
"r":0.7807762008,
"f":0.7985282783
},
"PublicTerms":{
"p":0.836052888,
"r":0.817152995,
"f":0.8264949072
},
"Negative":{
"p":0.7453163144,
"r":0.7163662664,
"f":0.7305545985
},
"InformationPlace":{
"p":0.8188157906,
"r":0.8335347567,
"f":0.8261097162
},
"Strategic":{
"p":0.7632035241,
"r":0.736729727,
"f":0.7497329945
},
"Description":{
"p":0.7401868131,
"r":0.7744252598,
"f":0.7569190491
},
"InformationChange":{
"p":0.7399110525,
"r":0.7320218834,
"f":0.735945326
},
"InformationTopics":{
"p":0.8012082075,
"r":0.8473905979,
"f":0.8236525463
},
"Positive":{
"p":0.7629533297,
"r":0.7206053443,
"f":0.7411749282
},
"Interactive":{
"p":0.8032971372,
"r":0.823861134,
"f":0.8134491919
},
"FirstPerson":{
"p":0.8886095598,
"r":0.9192571518,
"f":0.9036735814
},
"MetadiscourseInteractive":{
"p":0.8509951759,
"r":0.7454662487,
"f":0.7947428878
},
"CitationAuthority":{
"p":0.7465189873,
"r":0.6585093514,
"f":0.6997577495
},
"Citation":{
"p":0.8363710416,
"r":0.7871586009,
"f":0.8110189573
},
"Character":{
"p":0.8412782936,
"r":0.8525868789,
"f":0.846894837
},
"Facilitate":{
"p":0.7598171895,
"r":0.719405117,
"f":0.7390591282
},
"MetadiscourseCohesive":{
"p":0.9223458674,
"r":0.9489764826,
"f":0.9354716861
},
"Contingent":{
"p":0.8242590822,
"r":0.8244955532,
"f":0.8243773008
},
"Updates":{
"p":0.7947332138,
"r":0.7761559799,
"f":0.7853347503
},
"InformationStates":{
"p":0.8227134503,
"r":0.9112838451,
"f":0.8647366156
},
"Reasoning":{
"p":0.8396406267,
"r":0.8356578158,
"f":0.837644487
},
"ConfidenceHigh":{
"p":0.8263380824,
"r":0.7779590357,
"f":0.8014191019
},
"Future":{
"p":0.7687930642,
"r":0.7887530251,
"f":0.7786451511
},
"Inquiry":{
"p":0.7311205926,
"r":0.6527307144,
"f":0.6897054103
},
"Uncertainty":{
"p":0.795014061,
"r":0.6841072596,
"f":0.7354026787
},
"InformationChangePositive":{
"p":0.7706732528,
"r":0.6174875403,
"f":0.6856282552
},
"AcademicWritingMoves":{
"p":0.6962724724,
"r":0.5630168045,
"f":0.622594204
},
"InformationChangeNegative":{
"p":0.7627880832,
"r":0.5744320587,
"f":0.6553444945
},
"Responsibility":{
"p":0.738339772,
"r":0.6839486777,
"f":0.7101042139
},
"ConfidenceLow":{
"p":0.749034749,
"r":0.5655976676,
"f":0.6445182724
},
"CitationHedged":{
"p":0.6092307692,
"r":0.9406175772,
"f":0.7394957983
}
},
"tok2vec_loss":4150940.8609702764,
"tagger_loss":54146.3049736023,
"ner_loss":254954.859375
},
"requirements":[
"spacy>=3.8.6,<3.9.0"
]
}