{"id":"W2250713394","doi":"10.3115/v1/w15-0705","title":"GutenTag: an NLP-driven Tool for Digital Humanities Research in the Project Gutenberg Corpus","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Guelph","keywords":"Disk formatting; Metadata; Computer science; Digital humanities; Variety (cybernetics); Corpus linguistics; Natural language processing; World Wide Web; Software; Digital library; Artificial intelligence; Linguistics; Information retrieval; Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00135255,0.0001153539,0.0001161304,0.0002441318,0.0001436422,0.001335952,0.002158602,0.00006250839,0.000001283398],"category_scores_gemma":[0.0001854012,0.00007054665,0.0000366704,0.0005033335,0.0001125907,0.001956667,0.0003925085,0.0002480728,0.000008880435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008934712,"about_ca_system_score_gemma":0.0002073951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002403204,"about_ca_topic_score_gemma":0.0001402458,"domain_scores_codex":[0.9983764,0.0001304108,0.0001860682,0.0003453816,0.0005708782,0.000390835],"domain_scores_gemma":[0.9987499,0.0002208306,0.00004017312,0.0006119796,0.0003423395,0.00003483333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005030795,0.0003135209,0.001109096,0.00005883392,0.00001089108,0.00009399793,0.01686747,0.000003220723,0.0003601291,0.8522918,0.03976988,0.08907089],"study_design_scores_gemma":[0.001674751,0.003048762,0.0003723557,0.000163523,0.000007635975,0.0002522009,0.008203759,0.03456471,0.007260458,0.8710592,0.07235767,0.001034937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1405366,0.001994946,0.7931203,0.008921251,0.0008413517,0.007165377,0.00005770082,0.003630942,0.04373156],"genre_scores_gemma":[0.7156848,0.000003264738,0.2817146,0.0005408605,0.0001512131,0.0002645801,0.00001716322,0.00001474764,0.001608834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5751482,"threshold_uncertainty_score":0.9997008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2177205030712601,"score_gpt":0.4128816687996297,"score_spread":0.1951611657283696,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}