{"id":"W3098123193","doi":"10.18653/v1/2020.codi-1.13","title":"Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help !","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Huawei Technologies","keywords":"Automatic summarization; Transformer; Computer science; Artificial intelligence; Natural language processing; Sentence; Language model; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001225254,0.0001219439,0.0001517769,0.00006764571,0.00004446288,0.0001190928,0.0004507079,0.00005229466,0.0000113284],"category_scores_gemma":[0.00002271244,0.000106425,0.00006148723,0.0002231942,0.00001996795,0.0004955919,0.00003266822,0.0001028036,0.000003146664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004146359,"about_ca_system_score_gemma":0.00008098546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001832273,"about_ca_topic_score_gemma":0.0002452614,"domain_scores_codex":[0.9989358,0.00002874579,0.0001975195,0.0003938154,0.0001855351,0.0002585633],"domain_scores_gemma":[0.9994822,0.000100419,0.0000445112,0.0002315403,0.00002938822,0.0001119959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001859211,0.0002647786,0.01025214,0.0001704266,0.000109902,0.00004885053,0.05299462,0.04102508,0.004369103,0.4539349,0.001863095,0.4347812],"study_design_scores_gemma":[0.001279224,0.0001418429,0.001052195,0.00004651993,0.00001441237,0.000003033429,0.002752613,0.9741173,0.007043428,0.01142988,0.001712533,0.0004070657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02122669,0.00003265686,0.9313751,0.04547757,0.0001167227,0.000452099,0.000005884289,0.00008236885,0.001230877],"genre_scores_gemma":[0.8997015,0.00003347052,0.09884227,0.001087323,0.00003236896,0.00004872408,0.000003915927,0.00001031832,0.0002401638],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9330922,"threshold_uncertainty_score":0.4339885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04987185070598387,"score_gpt":0.2862067534909244,"score_spread":0.2363349027849405,"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."}}