{"id":"W2890419630","doi":"10.18653/v1/d18-1409","title":"BanditSum: Extractive Summarization as a Contextual Bandit","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Automatic summarization; Computer science; Artificial intelligence; Reinforcement learning; Context (archaeology); Sequence (biology); Natural language processing; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001701091,0.001892535,0.001484344,0.001390001,0.0008468312,0.001437343,0.00228835,0.001572953,0.005076963],"category_scores_gemma":[0.005307795,0.0006956427,0.001019719,0.001232054,0.0007329289,0.003030706,0.001459524,0.002112289,0.002245154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012638,"about_ca_system_score_gemma":0.001240752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003328055,"about_ca_topic_score_gemma":0.008259887,"domain_scores_codex":[0.9990802,0.0002912713,0.00006748531,0.0002930204,0.0001968376,0.00007112816],"domain_scores_gemma":[0.9982619,0.000907572,0.000183042,0.0002588603,0.0003169137,0.00007174892],"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":[0.0004000486,0.0002977807,0.0009509472,0.0004325318,0.0002439748,0.0001946519,0.0003384581,0.3551764,0.01818317,0.01168028,0.009402794,0.602699],"study_design_scores_gemma":[0.00002381968,0.0001295897,0.0001746313,0.00002463792,0.0000500474,0.00004250125,0.00003784212,0.9814341,0.006571828,0.007731069,0.003762569,0.00001719551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01103312,0.0008904437,0.9807909,0.0002749657,0.0001108744,0.0001541174,0.0002450417,0.004804108,0.001696495],"genre_scores_gemma":[0.2421103,0.000648341,0.7439243,0.0005434121,0.0003342292,0.0005922306,0.001939141,0.0008611662,0.009046959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005076963,"threshold_uncertainty_score":0.01698416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0206302257562439,"score_gpt":0.2686749282276282,"score_spread":0.2480447024713843,"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."}}