{"id":"W2953476352","doi":"10.1007/978-3-031-24337-0_24","title":"Multiplicative Models for Recurrent Language Modeling","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Recurrent neural network; Language model; Multiplicative function; Artificial intelligence; Relevance (law); Parametrization (atmospheric modeling); Simple (philosophy); Theoretical computer science; Artificial neural network; Natural language processing; Machine learning; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009623966,0.0005044691,0.0005220357,0.000721978,0.0002456565,0.0003656132,0.003543906,0.0002951001,0.000002137644],"category_scores_gemma":[0.0001239899,0.0004795005,0.0001908909,0.0004386525,0.0001869415,0.0006111621,0.00153376,0.0006530205,0.00003079998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003065246,"about_ca_system_score_gemma":0.0003929858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000270845,"about_ca_topic_score_gemma":0.00008608052,"domain_scores_codex":[0.9958352,0.00002078052,0.000573526,0.002012193,0.0008007904,0.0007574927],"domain_scores_gemma":[0.9970673,0.0005491402,0.0002208547,0.001688866,0.0003067458,0.0001671168],"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":[0.000003520663,0.000007575064,3.15923e-7,0.00002777001,0.000005678511,0.000009120844,0.001651473,0.5858209,0.000025714,0.04182951,0.000004148876,0.3706143],"study_design_scores_gemma":[0.0001614183,0.00006059793,2.769255e-7,0.0002291802,0.000004118914,0.000005895869,4.985273e-7,0.6852047,0.0001301413,0.3138008,0.00004037639,0.0003620789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003865866,0.0004200063,0.9950163,0.0006037886,0.001700182,0.0008332583,0.00001683082,0.0004255752,0.0009454113],"genre_scores_gemma":[0.07985134,0.00005518486,0.918083,0.0006030063,0.0006156791,0.00008560431,0.00001242075,0.00007374283,0.0006200508],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3702522,"threshold_uncertainty_score":0.9997657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05669957815851957,"score_gpt":0.2950025759639646,"score_spread":0.238302997805445,"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."}}