{ "lang":"en", "name":"docusco_spacy", "version":"1.3", "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":">=3.5.0,<3.6.0", "spacy_git_version":"Unknown", "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", "MC2", "MC221", "MC222", "MCMC", "MD", "MF", "ND1", "NN", "NN1", "NN121", "NN122", "NN131", "NN132", "NN133", "NN141", "NN142", "NN143", "NN144", "NN2", "NN21", "NN22", "NN221", "NN222", "NN231", "NN232", "NN233", "NN31", "NN32", "NN33", "NNA", "NNB", "NNL1", "NNL2", "NNO", "NNO2", "NNT1", "NNT131", "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":[ "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":0.9698599662, "ents_f":0.7971954516, "ents_p":0.798987704, "ents_r":0.7954112218, "ents_per_type":{ "Contingent":{ "p":0.818815331, "r":0.782463929, "f":0.8002270148 }, "InformationExposition":{ "p":0.8498392228, "r":0.857557341, "f":0.8536808374 }, "AcademicTerms":{ "p":0.8128432795, "r":0.8176600252, "f":0.8152445377 }, "ForceStressed":{ "p":0.8036501362, "r":0.7950043821, "f":0.7993038804 }, "Character":{ "p":0.8509934653, "r":0.8578615428, "f":0.8544137022 }, "Narrative":{ "p":0.7922994384, "r":0.7865517992, "f":0.789415157 }, "Strategic":{ "p":0.74291956, "r":0.7049416991, "f":0.7234325438 }, "MetadiscourseInteractive":{ "p":0.8243080626, "r":0.7077258639, "f":0.761581223 }, "Facilitate":{ "p":0.7420591457, "r":0.6909739929, "f":0.7156060206 }, "Negative":{ "p":0.7366169936, "r":0.6818932229, "f":0.7081995321 }, "Interactive":{ "p":0.8438560526, "r":0.8501978617, "f":0.8470150867 }, "MetadiscourseCohesive":{ "p":0.9307703425, "r":0.9246894967, "f":0.9277199553 }, "Description":{ "p":0.7184076094, "r":0.7692427259, "f":0.7429566137 }, "PublicTerms":{ "p":0.8250038862, "r":0.8023660141, "f":0.8135274957 }, "Reasoning":{ "p":0.8453436321, "r":0.8060425995, "f":0.8252254568 }, "Positive":{ "p":0.7428654449, "r":0.6843594646, "f":0.7124132921 }, "Updates":{ "p":0.7921472679, "r":0.7476358038, "f":0.7692481756 }, "InformationTopics":{ "p":0.7997236338, "r":0.8110942833, "f":0.8053688262 }, "ConfidenceHigh":{ "p":0.7693539348, "r":0.7862870234, "f":0.7777283211 }, "Citation":{ "p":0.8227242525, "r":0.7993544222, "f":0.8108709889 }, "ConfidenceHedged":{ "p":0.8354197349, "r":0.8900831633, "f":0.8618855884 }, "InformationChange":{ "p":0.7294003868, "r":0.7230371009, "f":0.7262048048 }, "InformationStates":{ "p":0.8306426735, "r":0.8544531415, "f":0.8423796861 }, "FirstPerson":{ "p":0.8819685753, "r":0.9076103856, "f":0.8946057773 }, "Responsibility":{ "p":0.7287275566, "r":0.6496172582, "f":0.6869021339 }, "Inquiry":{ "p":0.6458673322, "r":0.6369402632, "f":0.6413727359 }, "InformationChangeNegative":{ "p":0.738317757, "r":0.532285233, "f":0.6185970636 }, "ConfidenceLow":{ "p":0.8554216867, "r":0.5059382423, "f":0.6358208955 }, "InformationPlace":{ "p":0.8853535824, "r":0.8875035024, "f":0.8864272388 }, "Future":{ "p":0.7515119175, "r":0.7649827992, "f":0.758187528 }, "AcademicWritingMoves":{ "p":0.6664195701, "r":0.4892517007, "f":0.5642554527 }, "InformationReportVerbs":{ "p":0.7737441669, "r":0.8067978533, "f":0.7899253862 }, "Uncertainty":{ "p":0.7402862986, "r":0.6408700051, "f":0.6870001356 }, "CitationHedged":{ "p":0.7630662021, "r":0.9399141631, "f":0.8423076923 }, "CitationAuthority":{ "p":0.7866273353, "r":0.5972377753, "f":0.6789730533 }, "InformationChangePositive":{ "p":0.7317845829, "r":0.605592776, "f":0.6627350972 } }, "tok2vec_loss":209248.4752924392, "tagger_loss":13167.9055271149, "ner_loss":58184.6998399578 }, "requirements":[ ] }