{"id":"W4385571027","doi":"10.18653/v1/2023.acl-short.64","title":"Improving Automatic Quotation Attribution in Literary Novels","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Attribution; Coreference; Benchmark (surveying); Task (project management); Authorship attribution; Natural language processing; Character (mathematics); Identification (biology); Artificial intelligence; Set (abstract data type); Inference; Training set; Resolution (logic); Psychology; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006512755,0.001623036,0.001375169,0.003425088,0.00135776,0.002892613,0.002625747,0.002169483,0.002909994],"category_scores_gemma":[0.02488805,0.0005936021,0.001104232,0.00186969,0.0009479775,0.005317512,0.003098135,0.002383612,0.004335598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001019781,"about_ca_system_score_gemma":0.001552772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004468019,"about_ca_topic_score_gemma":0.006003317,"domain_scores_codex":[0.9959454,0.001459277,0.0003068368,0.001500643,0.0005359638,0.0002519652],"domain_scores_gemma":[0.9868217,0.008135526,0.0009483253,0.001655785,0.00203366,0.0004051057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009849502,0.0007362764,0.03003393,0.001314694,0.0004119472,0.0007581946,0.002026055,0.06447276,0.01941122,0.004130548,0.02899056,0.8467289],"study_design_scores_gemma":[0.00005576845,0.0001284611,0.00734792,0.0001113784,0.00009763764,0.0003247132,0.0009986134,0.9583852,0.01575445,0.008818736,0.007918521,0.00005855418],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5841258,0.01026456,0.3531844,0.003236026,0.001863056,0.000326964,0.003802878,0.03240192,0.01079445],"genre_scores_gemma":[0.8771364,0.0008767675,0.1060047,0.0003882672,0.0004690311,0.00009183792,0.007565041,0.0007517323,0.006716184],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006512755,"threshold_uncertainty_score":0.0344432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01426556640817654,"score_gpt":0.2774959925160585,"score_spread":0.2632304261078819,"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."}}