{"id":"W3096783161","doi":"10.18653/v1/2020.coling-main.495","title":"WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Automatic summarization; Computer science; Leverage (statistics); Task (project management); Multi-document summarization; Set (abstract data type); Information retrieval; Sentence; Artificial intelligence; Training set; Similarity (geometry); Natural language processing","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004486689,0.0005351721,0.000574995,0.0001598818,0.0002542365,0.0007041261,0.001287642,0.000309707,0.00004547155],"category_scores_gemma":[0.0001577355,0.0004466864,0.000206026,0.0002130006,0.00003486382,0.0006637882,0.001378732,0.0008474082,0.00001968563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001891887,"about_ca_system_score_gemma":0.0004127294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005593901,"about_ca_topic_score_gemma":0.000167428,"domain_scores_codex":[0.9963751,0.0001467687,0.0006660865,0.001664113,0.0006469306,0.0005009579],"domain_scores_gemma":[0.9978396,0.0002703782,0.00031218,0.0009761422,0.0003744799,0.0002272361],"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":[0.0009788964,0.0009581098,0.005672633,0.00294212,0.00101759,0.0001621034,0.02820147,0.58255,0.01633758,0.08605182,0.001072507,0.2740552],"study_design_scores_gemma":[0.001342485,0.0002328792,0.0005282236,0.0003009998,0.00004416155,0.00000235811,0.0004767732,0.9894218,0.003049679,0.003024151,0.0008867384,0.0006897807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009379225,0.00008730289,0.9845011,0.002542852,0.0005776376,0.001672525,0.00001386654,0.0006346407,0.0005909026],"genre_scores_gemma":[0.5276158,0.00004052893,0.4711664,0.0001845822,0.0001358649,0.000223892,0.0001772186,0.00005280928,0.0004028953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5182366,"threshold_uncertainty_score":0.9997985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04232295421965686,"score_gpt":0.2720480447994884,"score_spread":0.2297250905798315,"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."}}