{ "lang":"en", "name":"docusco_spacy_cd", "version":"1.2", "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_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", "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", "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", "NN33", "NNA", "NNB", "NNL1", "NNL2", "NNO", "NNO2", "NNT1", "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", "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", "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", "CitationHedged", "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":0.9734866573, "ents_f":0.7826346995, "ents_p":0.7896141572, "ents_r":0.7757775447, "ents_per_type":{ "ActorsFirstPerson":{ "p":0.8180863993, "r":0.8443950279, "f":0.8310325477 }, "ActorsPeople":{ "p":0.855646716, "r":0.8830180997, "f":0.8691169573 }, "CitationNeutral":{ "p":0.7527158376, "r":0.7425267908, "f":0.7475865985 }, "SentimentNegative":{ "p":0.7090227054, "r":0.6414706491, "f":0.6735571909 }, "ActorsAbstractions":{ "p":0.7691966267, "r":0.8180602299, "f":0.7928762968 }, "PlanningStrategy":{ "p":0.721360087, "r":0.6471005497, "f":0.6822154709 }, "SignpostingAcademicWritingMoves":{ "p":0.6508373967, "r":0.5615511249, "f":0.60290652 }, "OrganizationNarrative":{ "p":0.7794650481, "r":0.7044971007, "f":0.74008743 }, "PlanningFuture":{ "p":0.7692376361, "r":0.7372518823, "f":0.7529051988 }, "ConfidenceHedged":{ "p":0.8042735043, "r":0.7942268737, "f":0.7992186173 }, "SentimentPositive":{ "p":0.7252046892, "r":0.6383048418, "f":0.678985594 }, "StanceEmphatic":{ "p":0.7869956077, "r":0.8246021505, "f":0.8053601059 }, "SignpostingMetadiscourse":{ "p":0.9005463375, "r":0.8505900903, "f":0.8748556405 }, "CitationControversy":{ "p":0.7772643253, "r":0.7109044801, "f":0.7426048565 }, "ActorsPublicEntities":{ "p":0.8000974738, "r":0.7844855049, "f":0.7922145816 }, "OrganizationReasoning":{ "p":0.8085699285, "r":0.8050261359, "f":0.8067941408 }, "ConfidenceHigh":{ "p":0.7475272184, "r":0.7257841647, "f":0.7364952501 }, "CitationAuthority":{ "p":0.7098366882, "r":0.6263404826, "f":0.6654797935 }, "StanceModerated":{ "p":0.7352631579, "r":0.7569764292, "f":0.7459618209 } }, "tok2vec_loss":59374.2493771126, "tagger_loss":11360.4048709869, "ner_loss":39417.2632061559 }, "spacy_version":">=3.5.0,<3.6.0", "requirements":[ ] }