browndw's picture
Update spaCy pipeline
34e3059 verified
{
"lang":"en",
"name":"docusco_spacy_trf",
"version":"1.4",
"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":">=3.7.4,<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",
"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",
"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":[
"transformer",
"tagger",
"ner"
],
"components":[
"transformer",
"tagger",
"ner"
],
"disabled":[
],
"performance":{
"tag_acc":0.9833005069,
"ents_f":0.89489127,
"ents_p":0.8936849894,
"ents_r":0.8961008114,
"ents_per_type":{
"Interactive":{
"p":0.9038147042,
"r":0.9085791891,
"f":0.9061906841
},
"Strategic":{
"p":0.8731209791,
"r":0.8729839975,
"f":0.8730524829
},
"InformationExposition":{
"p":0.9378152461,
"r":0.9425424362,
"f":0.9401728991
},
"Description":{
"p":0.8603086783,
"r":0.8628561455,
"f":0.8615805288
},
"Character":{
"p":0.8970552523,
"r":0.9059317787,
"f":0.9014716649
},
"Negative":{
"p":0.8490897231,
"r":0.8482747998,
"f":0.8486820658
},
"ForceStressed":{
"p":0.8974732161,
"r":0.9062850844,
"f":0.901857626
},
"Positive":{
"p":0.8670176129,
"r":0.8543794441,
"f":0.860652135
},
"Contingent":{
"p":0.9095543496,
"r":0.9151981468,
"f":0.9123675203
},
"Narrative":{
"p":0.9071942585,
"r":0.9115067079,
"f":0.9093453704
},
"Responsibility":{
"p":0.8367471721,
"r":0.8236533253,
"f":0.83014862
},
"FirstPerson":{
"p":0.942293645,
"r":0.9524981541,
"f":0.9473684211
},
"MetadiscourseCohesive":{
"p":0.9664418702,
"r":0.9675970795,
"f":0.9670191299
},
"InformationStates":{
"p":0.9135818849,
"r":0.9337763313,
"f":0.92356873
},
"InformationChangePositive":{
"p":0.8092221941,
"r":0.7985,
"f":0.8038253429
},
"InformationPlace":{
"p":0.8869565217,
"r":0.8637608966,
"f":0.8752050473
},
"PublicTerms":{
"p":0.9106099935,
"r":0.9051181991,
"f":0.9078557912
},
"ConfidenceHedged":{
"p":0.9312491632,
"r":0.9472286531,
"f":0.9391709425
},
"Updates":{
"p":0.8900253355,
"r":0.8847947761,
"f":0.8874023483
},
"AcademicTerms":{
"p":0.9047579038,
"r":0.9041067959,
"f":0.9044322327
},
"InformationChange":{
"p":0.8626154826,
"r":0.8744550299,
"f":0.8684949082
},
"Reasoning":{
"p":0.9153005464,
"r":0.9201892263,
"f":0.9177383761
},
"Inquiry":{
"p":0.8400098103,
"r":0.8355017076,
"f":0.8377496943
},
"InformationTopics":{
"p":0.9011336572,
"r":0.9038373337,
"f":0.9024834706
},
"InformationChangeNegative":{
"p":0.7965116279,
"r":0.802734375,
"f":0.7996108949
},
"CitationAuthority":{
"p":0.8592772759,
"r":0.8215946844,
"f":0.840013587
},
"MetadiscourseInteractive":{
"p":0.9046108081,
"r":0.896785609,
"f":0.9006812124
},
"Citation":{
"p":0.9161283259,
"r":0.9187438234,
"f":0.9174342105
},
"Future":{
"p":0.8936464088,
"r":0.9047619048,
"f":0.8991698058
},
"InformationReportVerbs":{
"p":0.9019871599,
"r":0.9078712536,
"f":0.9049196418
},
"AcademicWritingMoves":{
"p":0.7788392644,
"r":0.7696483361,
"f":0.7742165242
},
"ConfidenceHigh":{
"p":0.9006732838,
"r":0.8966899316,
"f":0.8986771937
},
"Uncertainty":{
"p":0.8604228234,
"r":0.8565286264,
"f":0.8584713087
},
"Facilitate":{
"p":0.8591405681,
"r":0.8717114987,
"f":0.865380383
},
"ConfidenceLow":{
"p":0.8442367601,
"r":0.7207446809,
"f":0.7776183644
},
"CitationHedged":{
"p":0.8851351351,
"r":0.9034482759,
"f":0.8941979522
}
},
"transformer_loss":92562.0406026107,
"tagger_loss":17646.7661392662,
"ner_loss":70220.0462693061
},
"requirements":[
"spacy-transformers>=1.3.5,<1.4.0"
]
}