{"id":"W2973475963","doi":"10.18653/v1/d19-1389","title":"BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Army Research Office; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Samsung; Allen Institute for Artificial Intelligence; Naval Information Warfare Center Pacific; National Science Foundation","keywords":"Automatic summarization; Computer science; Sentence; Bottleneck; Artificial intelligence; Natural language processing; Information bottleneck method; Language model; Machine learning; Cluster analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003550904,0.002490229,0.002077957,0.003154537,0.001114631,0.002182528,0.003804371,0.001740797,0.007138908],"category_scores_gemma":[0.007979074,0.0009264731,0.00186738,0.002297244,0.0006502266,0.004064191,0.003140683,0.002122241,0.006764681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006545219,"about_ca_system_score_gemma":0.001636771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003248018,"about_ca_topic_score_gemma":0.006341075,"domain_scores_codex":[0.997867,0.0008240759,0.0001423564,0.0005716844,0.0004554023,0.0001394272],"domain_scores_gemma":[0.9963285,0.001728287,0.0002113109,0.0006805696,0.0009070406,0.0001442005],"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":[0.0009379241,0.0003707653,0.0006261347,0.0008078774,0.0005643051,0.0002215008,0.0004185599,0.03162588,0.02169668,0.007675164,0.09799638,0.8370588],"study_design_scores_gemma":[0.0002731114,0.0003396428,0.001135028,0.00008049794,0.000270032,0.0001360066,0.0002090057,0.9054461,0.02538578,0.0372687,0.02934709,0.000108894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007117646,0.001395109,0.9668573,0.0003666036,0.0004817496,0.0003167301,0.002607034,0.01931176,0.001546146],"genre_scores_gemma":[0.07677729,0.0006224163,0.8846545,0.0003520815,0.0006303979,0.0008780257,0.02190214,0.003490126,0.01069304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007138908,"threshold_uncertainty_score":0.02388203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02705406852004068,"score_gpt":0.2545242226792956,"score_spread":0.2274701541592549,"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."}}