{ "lang":"en", "name":"docusco_spacy", "version":"1.2", "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":0.9422182346, "ents_f":0.7901353181, "ents_p":0.7897948078, "ents_r":0.7904761222, "ents_per_type":{ "Contingent":{ "p":0.8286840509, "r":0.7583240844, "f":0.791944364 }, "InformationExposition":{ "p":0.8400248832, "r":0.8577633567, "f":0.8488014542 }, "AcademicTerms":{ "p":0.7894026371, "r":0.8286671247, "f":0.8085584799 }, "ForceStressed":{ "p":0.7898256456, "r":0.7841148116, "f":0.7869598681 }, "Character":{ "p":0.8500444492, "r":0.8432579053, "f":0.8466375774 }, "Narrative":{ "p":0.7737338187, "r":0.7965586415, "f":0.7849803462 }, "Strategic":{ "p":0.7364217252, "r":0.6996483435, "f":0.7175642072 }, "MetadiscourseInteractive":{ "p":0.8356010661, "r":0.6838480083, "f":0.7521464646 }, "Facilitate":{ "p":0.7088353414, "r":0.6600373959, "f":0.6835665874 }, "Negative":{ "p":0.7095155684, "r":0.682564777, "f":0.6957792879 }, "Interactive":{ "p":0.839874111, "r":0.8383435157, "f":0.8391081154 }, "MetadiscourseCohesive":{ "p":0.9192184725, "r":0.9288534712, "f":0.9240108556 }, "Description":{ "p":0.7208328088, "r":0.7628920157, "f":0.7412662853 }, "PublicTerms":{ "p":0.8309137834, "r":0.778781465, "f":0.8040034337 }, "Reasoning":{ "p":0.8395115952, "r":0.7998493535, "f":0.8192006857 }, "Positive":{ "p":0.7291883827, "r":0.6821606119, "f":0.7048909876 }, "Updates":{ "p":0.7837246077, "r":0.7084891137, "f":0.7442102224 }, "InformationTopics":{ "p":0.7918713029, "r":0.8200456611, "f":0.8057122551 }, "ConfidenceHigh":{ "p":0.7615851193, "r":0.7704958272, "f":0.7660145605 }, "Citation":{ "p":0.8037907101, "r":0.7775338928, "f":0.7904443132 }, "ConfidenceHedged":{ "p":0.8374410068, "r":0.8770594696, "f":0.856792489 }, "InformationChange":{ "p":0.7123025371, "r":0.7132585562, "f":0.7127802261 }, "InformationStates":{ "p":0.8041805777, "r":0.8789930188, "f":0.8399241946 }, "FirstPerson":{ "p":0.8766524888, "r":0.8892257463, "f":0.882894356 }, "Responsibility":{ "p":0.7242662257, "r":0.6096033403, "f":0.6620064236 }, "Inquiry":{ "p":0.6661799979, "r":0.6047524378, "f":0.6339817388 }, "InformationChangeNegative":{ "p":0.6824946846, "r":0.5407074677, "f":0.6033834586 }, "ConfidenceLow":{ "p":0.6462395543, "r":0.5510688836, "f":0.5948717949 }, "InformationPlace":{ "p":0.865587996, "r":0.8944517093, "f":0.8797831779 }, "InformationReportVerbs":{ "p":0.7508147746, "r":0.7912701252, "f":0.7705117932 }, "Future":{ "p":0.756072781, "r":0.7410827449, "f":0.7485027202 }, "AcademicWritingMoves":{ "p":0.7083700441, "r":0.4375510204, "f":0.5409587889 }, "Uncertainty":{ "p":0.7549221275, "r":0.6497218007, "f":0.6983824929 }, "CitationHedged":{ "p":0.7483221477, "r":0.9570815451, "f":0.8399246704 }, "CitationAuthority":{ "p":0.7841151386, "r":0.5490854797, "f":0.6458836443 }, "InformationChangePositive":{ "p":0.7640586797, "r":0.546169531, "f":0.6369967725 } }, "tok2vec_loss":180447.6574847773, "tagger_loss":24009.219291687, "ner_loss":59358.4819319265 }, "requirements":[ ] }