{"id":"W3114178959","doi":"10.18653/v1/2020.aacl-main.51","title":"Systematically Exploring Redundancy Reduction in Summarizing Long Documents","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Redundancy (engineering); Automatic summarization; Computer science; Context (archaeology); Artificial intelligence; Information retrieval; Natural language processing; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002317141,0.0000845552,0.0001413403,0.00006179168,0.00004082465,0.0001563682,0.0004356719,0.00002733833,0.0000127243],"category_scores_gemma":[0.00006444485,0.00008042488,0.00002888933,0.0003094584,0.00000652741,0.001135041,0.0002237961,0.000113082,0.0000627249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006095968,"about_ca_system_score_gemma":0.00002691936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004985002,"about_ca_topic_score_gemma":0.000004980297,"domain_scores_codex":[0.9988294,0.00005153198,0.0003380801,0.0003450506,0.000230595,0.0002053182],"domain_scores_gemma":[0.9995307,0.00002177298,0.00004678787,0.0002837716,0.00002453958,0.00009238088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002512621,0.0001602589,0.01617935,0.001939175,0.00006786988,0.0002611121,0.02690342,0.0167712,0.01427356,0.7086763,0.0005476937,0.2141949],"study_design_scores_gemma":[0.0007337152,0.0000857103,0.001645259,0.0006816544,0.00000666944,0.00003728756,0.0007482784,0.9850572,0.005880249,0.004367758,0.0002907329,0.0004655349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1032658,0.00004479063,0.888801,0.002566105,0.0003851497,0.0001691799,4.170807e-8,0.0002132527,0.004554654],"genre_scores_gemma":[0.9188035,0.000006913168,0.08082849,0.0001336065,0.00009311496,0.00002485678,2.637971e-7,0.000005656752,0.0001036197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.968286,"threshold_uncertainty_score":0.3279631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09334047331948332,"score_gpt":0.265490464442501,"score_spread":0.1721499911230177,"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."}}