{"id":"W2963412005","doi":"10.18653/v1/d16-1233","title":"Conditional Generation and Snapshot Learning in Neural Dialogue Systems","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Institute for Catastrophic Loss Reduction","keywords":"Snapshot (computer storage); Computer science; Artificial intelligence; Artificial neural network; Natural language processing; Cognitive science; Machine learning; Psychology; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001270322,0.00003654131,0.0000464892,0.0000408477,0.00003248242,0.00005932929,0.00008166341,0.00002086227,0.00001245879],"category_scores_gemma":[0.00002152428,0.0000245368,0.000006285836,0.00003679559,0.0000096227,0.0002944407,0.00004655078,0.0000327684,0.000005671484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001578406,"about_ca_system_score_gemma":0.00001207986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000483357,"about_ca_topic_score_gemma":0.00002065897,"domain_scores_codex":[0.9995477,0.00004356619,0.00009537199,0.0001520343,0.00007742579,0.00008396992],"domain_scores_gemma":[0.9998198,0.00004502536,0.0000182686,0.00007765991,0.00001502789,0.00002421197],"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":[0.000002183405,0.00002073666,0.05153539,0.00001297269,0.000006301575,0.00002047568,0.0005179042,0.04070072,0.04320318,0.7999123,0.0007039228,0.06336394],"study_design_scores_gemma":[0.0001722347,0.00001209357,0.004474502,0.000004862923,2.696209e-7,0.00001127239,0.000004311392,0.9943558,0.000206759,0.000471655,0.0002373312,0.00004892004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2744969,0.00004573946,0.7239234,0.000770168,0.0001777661,0.00004190398,3.689754e-7,0.00003394927,0.0005097777],"genre_scores_gemma":[0.9973604,0.000003280472,0.002180865,0.00007848472,0.00009873266,0.000006554809,0.000004280729,0.000001463297,0.000265907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9536551,"threshold_uncertainty_score":0.1000582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0388995657737141,"score_gpt":0.2375652178747476,"score_spread":0.1986656521010335,"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."}}