{ "lang":"en", "name":"docusco_spacy_cd", "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":{ "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", "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":[ "tok2vec", "tagger", "ner" ], "components":[ "tok2vec", "tagger", "ner" ], "disabled":[ ], "performance":{ "tag_acc":0.9763683149, "ents_f":0.8139802353, "ents_p":0.8206658604, "ents_r":0.80740266, "ents_per_type":{ "ActorsPeople":{ "p":0.8542168374, "r":0.8696353974, "f":0.8618571637 }, "ActorsPublicEntities":{ "p":0.8169841646, "r":0.8246103931, "f":0.8207795646 }, "OrganizationReasoning":{ "p":0.8497536946, "r":0.8395089039, "f":0.8446002337 }, "ActorsFirstPerson":{ "p":0.8645147555, "r":0.8759769676, "f":0.8702081187 }, "ConfidenceHedged":{ "p":0.8414330099, "r":0.849020822, "f":0.8452098865 }, "SentimentPositive":{ "p":0.7541410809, "r":0.6988926856, "f":0.7254665342 }, "SignpostingMetadiscourse":{ "p":0.9222331178, "r":0.8799657453, "f":0.9006037785 }, "ActorsAbstractions":{ "p":0.812620511, "r":0.8397741356, "f":0.825974217 }, "CitationAuthority":{ "p":0.7421895511, "r":0.6606683805, "f":0.6990603363 }, "SentimentNegative":{ "p":0.7569732066, "r":0.681115792, "f":0.7170438069 }, "OrganizationNarrative":{ "p":0.8146691347, "r":0.7606297812, "f":0.7867225698 }, "StanceEmphatic":{ "p":0.8325835219, "r":0.8587117676, "f":0.8454458216 }, "ConfidenceHigh":{ "p":0.793492611, "r":0.7964435325, "f":0.7949653333 }, "PlanningFuture":{ "p":0.8015720524, "r":0.7731229292, "f":0.7870905037 }, "SignpostingAcademicWritingMoves":{ "p":0.6799470549, "r":0.6417239225, "f":0.6602827763 }, "PlanningStrategy":{ "p":0.7405392335, "r":0.7067443605, "f":0.7232472325 }, "CitationNeutral":{ "p":0.8012995179, "r":0.7580805076, "f":0.7790910944 }, "StanceModerated":{ "p":0.8127539304, "r":0.8244042286, "f":0.8185376268 }, "CitationControversy":{ "p":0.7450381679, "r":0.7160674982, "f":0.7302656192 } }, "tok2vec_loss":1509739.3996848087, "tagger_loss":39368.7426280975, "ner_loss":127428.554314194 }, "requirements":[ ] }