{"id":"W2951108824","doi":"","title":"Gated Orthogonal Recurrent Units: On Learning to Forget","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Recurrent neural network; Computer science; Forgetting; Treebank; Artificial intelligence; Benchmark (surveying); TIMIT; Natural language processing; Parsing; Speech recognition; Artificial neural network; Hidden Markov model; Cognitive psychology","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":[0.0003306923,0.0003238763,0.0003133259,0.0003288957,0.000375367,0.0002241017,0.002781838,0.0002449969,0.00001273404],"category_scores_gemma":[0.0002023088,0.0003785676,0.0001249206,0.0003648463,0.00004182609,0.0002551174,0.00303045,0.001047086,0.0001543768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002208639,"about_ca_system_score_gemma":0.0003023556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008680419,"about_ca_topic_score_gemma":0.00005748101,"domain_scores_codex":[0.9977543,0.000154305,0.0001912855,0.001321402,0.0001508627,0.0004278166],"domain_scores_gemma":[0.9973262,0.00008229059,0.0002763241,0.00177289,0.0002670713,0.0002752432],"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":[0.00004524428,0.00005579739,0.001853995,0.00004469343,0.00006092587,0.0003038492,0.0005518295,0.8189765,0.0000113301,0.1645179,0.0004463202,0.01313169],"study_design_scores_gemma":[0.0004144722,0.000169353,0.0008736037,0.0003978964,0.00003126547,0.000003672358,0.00006216141,0.9673693,0.00008104176,0.01552152,0.01438917,0.0006864977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3870078,0.00001834039,0.6057823,0.000246046,0.001103379,0.0002563142,0.000008065091,0.0002997635,0.005278023],"genre_scores_gemma":[0.9937101,0.00004670658,0.00221104,0.0001327966,0.0001196855,8.60737e-7,0.00001929852,0.00001887485,0.003740639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6067023,"threshold_uncertainty_score":0.9998666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1370948104062215,"score_gpt":0.2172512389434832,"score_spread":0.08015642853726165,"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."}}