{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003207931,0.001956167,0.002370423,0.00684001,0.001331054,0.002134518,0.002060178,0.001265992,0.002034229],"category_scores_gemma":[0.0131467,0.0007499537,0.001411872,0.005613565,0.000731533,0.003829468,0.001914673,0.00117926,0.001670064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005124386,"about_ca_system_score_gemma":0.001692274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002726055,"about_ca_topic_score_gemma":0.005178732,"domain_scores_codex":[0.9973999,0.001180982,0.0002439118,0.0005147342,0.0004996592,0.0001608818],"domain_scores_gemma":[0.9895988,0.006814296,0.000533265,0.001025775,0.00179397,0.0002339445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001018585,0.0005013674,0.005503764,0.002560018,0.0007551671,0.0006196561,0.001471887,0.03764346,0.03244722,0.007152612,0.04092339,0.8694028],"study_design_scores_gemma":[0.000285808,0.00133033,0.006573664,0.0005232776,0.001725892,0.0008572292,0.002334753,0.8144544,0.0397919,0.09341091,0.03853064,0.0001811644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1490912,0.02380577,0.8089432,0.001992175,0.0006142117,0.0005653398,0.005220441,0.005978072,0.003789632],"genre_scores_gemma":[0.3344409,0.004210667,0.6353054,0.0004063599,0.0008656408,0.000466197,0.02029854,0.0008914245,0.003114861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00684001,"threshold_uncertainty_score":0.01696539,"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."}}