{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008053688,0.001008803,0.0008452925,0.000396662,0.0002908286,0.0008855386,0.00174485,0.001022587,0.004829179],"category_scores_gemma":[0.003955749,0.0005376849,0.0006217228,0.0005494383,0.001024024,0.002425263,0.001421616,0.001847861,0.001317076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006490636,"about_ca_system_score_gemma":0.0006102368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004012519,"about_ca_topic_score_gemma":0.004196561,"domain_scores_codex":[0.9996152,0.0001021291,0.00002609318,0.000130887,0.00008245475,0.00004316669],"domain_scores_gemma":[0.9991094,0.0004224173,0.0000937526,0.0001983919,0.0001276459,0.00004832575],"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":[0.0002641205,0.00008313419,0.001395482,0.0002025405,0.0001256472,0.0002549365,0.0001521555,0.5099719,0.009012284,0.1201248,0.01021782,0.3481951],"study_design_scores_gemma":[0.000007784869,0.00003608473,0.0001117256,0.00001144148,0.00001343687,0.00002869784,0.000004433359,0.9621861,0.000998111,0.03453241,0.00206251,0.000007204663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03050353,0.002306876,0.9566413,0.001261719,0.0003250807,0.00004144989,0.0002786597,0.001706275,0.006934963],"genre_scores_gemma":[0.7969809,0.002558642,0.1733251,0.0007571685,0.0003938655,0.0002160653,0.0009443306,0.0004513951,0.02437258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004829179,"threshold_uncertainty_score":0.01615518,"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."}}