{"id":"W3118454345","doi":"","title":"On-the-Fly Attention Modularization for Neural Generation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Fluency; Computer science; Modular programming; Artificial intelligence; Artificial neural network; Sentence; Natural language processing; Inference; Cognitive psychology; Machine learning; Psychology; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007790567,0.0005873372,0.0004872597,0.0004417674,0.0002765181,0.0006041462,0.001303308,0.000670983,0.003510496],"category_scores_gemma":[0.003663364,0.0003337694,0.0007329363,0.0003996988,0.0006919532,0.001750061,0.001615745,0.001335537,0.0008948364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006676879,"about_ca_system_score_gemma":0.0007139865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001233356,"about_ca_topic_score_gemma":0.00255433,"domain_scores_codex":[0.9996372,0.0001183494,0.00002324588,0.00010589,0.00007053234,0.00004469127],"domain_scores_gemma":[0.9989649,0.0004877444,0.00006971783,0.0003185947,0.0001009379,0.00005814797],"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":[0.0002523385,0.0001892926,0.001852028,0.000238098,0.000148695,0.0002218974,0.0004148637,0.3151971,0.04889339,0.05497792,0.00636327,0.5712511],"study_design_scores_gemma":[0.00001971066,0.00003012904,0.0001812944,0.00000727134,0.00001986541,0.00002998666,0.00001543833,0.952054,0.007887152,0.03848817,0.001260065,0.000006931846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03296469,0.0001937553,0.9610924,0.0002550579,0.00003925701,0.0000531351,0.0001061995,0.003460138,0.001835306],"genre_scores_gemma":[0.6883624,0.0001941906,0.3074568,0.0002184938,0.00008330741,0.0001669897,0.0003583548,0.0005430414,0.002616432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003510496,"threshold_uncertainty_score":0.01174378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1286590551685338,"score_gpt":0.1898030284534296,"score_spread":0.06114397328489579,"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."}}