browndw's picture
Update spaCy pipeline
7308f56 verified
{
"lang":"en",
"name":"docusco_spacy_cd_trf",
"version":"1.3",
"description":"English pipeline for part-of-speech and rhetorical tagging using a smaller 'common dictionary'.",
"author":"David Brown",
"email":"dwb2@andrew.cmu.edu",
"url":"https://docuscope.github.io",
"license":"MIT",
"spacy_version":">=3.7.4,<3.8.0",
"spacy_git_version":"bff8725f4",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"transformer":[
],
"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",
"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",
"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":[
"ActorsAbstractions",
"ActorsFirstPerson",
"ActorsPeople",
"ActorsPublicEntities",
"CitationAuthority",
"CitationControversy",
"CitationNeutral",
"ConfidenceHedged",
"ConfidenceHigh",
"OrganizationNarrative",
"OrganizationReasoning",
"PlanningFuture",
"PlanningStrategy",
"SentimentNegative",
"SentimentPositive",
"SignpostingAcademicWritingMoves",
"SignpostingMetadiscourse",
"StanceEmphatic",
"StanceModerated"
]
},
"pipeline":[
"transformer",
"tagger",
"ner"
],
"components":[
"transformer",
"tagger",
"ner"
],
"disabled":[
],
"performance":{
"tag_acc":0.9860324848,
"ents_f":0.8986060124,
"ents_p":0.8975978922,
"ents_r":0.8996163997,
"ents_per_type":{
"ActorsFirstPerson":{
"p":0.9297243488,
"r":0.9421626555,
"f":0.9359021772
},
"OrganizationNarrative":{
"p":0.8982249764,
"r":0.9052289888,
"f":0.901713382
},
"ConfidenceHedged":{
"p":0.9133998382,
"r":0.925173412,
"f":0.9192489282
},
"StanceEmphatic":{
"p":0.9163952226,
"r":0.9306501792,
"f":0.9234676931
},
"ActorsPeople":{
"p":0.9048275066,
"r":0.9085233815,
"f":0.9066716777
},
"SignpostingMetadiscourse":{
"p":0.9521945378,
"r":0.9343999277,
"f":0.9432133122
},
"PlanningStrategy":{
"p":0.867487328,
"r":0.8729657518,
"f":0.8702179177
},
"OrganizationReasoning":{
"p":0.9162113643,
"r":0.913893106,
"f":0.9150507669
},
"ActorsAbstractions":{
"p":0.8978776116,
"r":0.9052445851,
"f":0.9015460488
},
"SentimentPositive":{
"p":0.8603518268,
"r":0.8566270255,
"f":0.8584853859
},
"SentimentNegative":{
"p":0.8577821301,
"r":0.8418267418,
"f":0.8497295439
},
"CitationAuthority":{
"p":0.8555627846,
"r":0.8453873353,
"f":0.8504446241
},
"StanceModerated":{
"p":0.8848971874,
"r":0.9246727587,
"f":0.9043478261
},
"ConfidenceHigh":{
"p":0.8963930348,
"r":0.9093432591,
"f":0.9028217093
},
"CitationControversy":{
"p":0.8772563177,
"r":0.9109653233,
"f":0.8937931034
},
"CitationNeutral":{
"p":0.9121713201,
"r":0.9254675468,
"f":0.9187713311
},
"PlanningFuture":{
"p":0.891873065,
"r":0.915613826,
"f":0.9035875319
},
"ActorsPublicEntities":{
"p":0.9129542262,
"r":0.9113132257,
"f":0.9121329879
},
"SignpostingAcademicWritingMoves":{
"p":0.7986216171,
"r":0.8133881185,
"f":0.8059372349
}
},
"transformer_loss":46711.3121389837,
"tagger_loss":14058.3003581261,
"ner_loss":41682.5447270232
},
"requirements":[
"spacy-transformers>=1.3.5,<1.4.0"
]
}