{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005599767,0.0003064312,0.0002735287,0.0001518047,0.0002061076,0.0008859764,0.001313174,0.0002590423,0.0000134701],"category_scores_gemma":[0.00005299273,0.0002306413,0.00007973947,0.0002207656,0.00003299553,0.001787356,0.002850297,0.0004239029,0.00002330859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263702,"about_ca_system_score_gemma":0.0003376329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002654704,"about_ca_topic_score_gemma":0.00001080646,"domain_scores_codex":[0.9979782,0.0001244383,0.0005397198,0.0005315797,0.0005059844,0.0003200722],"domain_scores_gemma":[0.9978445,0.00008608717,0.0002454517,0.001493877,0.0002453179,0.00008483457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002839379,0.0002532564,0.03628899,0.00255815,0.0003561814,0.000008353696,0.02518624,0.6272282,0.001262165,0.2312972,0.0004884551,0.07504439],"study_design_scores_gemma":[0.0002623208,0.00001068689,0.001085018,0.0000836178,0.00002089258,0.000009572002,0.00008876435,0.99547,0.0001388902,0.001427553,0.001113156,0.0002894844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1083807,0.0001039189,0.8875636,0.0007636441,0.0008445886,0.0008264903,0.000005814265,0.0003325838,0.0011787],"genre_scores_gemma":[0.6188774,0.0002411894,0.379315,0.001172756,0.000132289,0.00003447949,0.00005214656,0.00002160314,0.0001531514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5104967,"threshold_uncertainty_score":0.9405281,"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."}}