{"id":"W1993378086","doi":"10.1145/2806416.2806493","title":"A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":467,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Nvidia","keywords":"Computer science; Encoder; Generative grammar; Context (archaeology); Artificial intelligence; Generative model; Natural language processing","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":[],"consensus_categories":[],"category_scores_codex":[0.0003847002,0.0001259146,0.0001336572,0.00008065117,0.00008246014,0.0002395072,0.0005677685,0.00004116348,0.00001502514],"category_scores_gemma":[0.00007027773,0.0001008059,0.00005351002,0.0001501428,0.00003483609,0.0007575096,0.0002902498,0.00008385667,0.00007087895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004468984,"about_ca_system_score_gemma":0.00007680606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002322277,"about_ca_topic_score_gemma":0.00006038155,"domain_scores_codex":[0.9988868,0.00005849691,0.0001817978,0.0003953283,0.0002330493,0.0002445053],"domain_scores_gemma":[0.9992329,0.00007664128,0.00004770684,0.0003518482,0.0001396042,0.0001513246],"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":[0.00002418011,0.0001353123,0.00007618005,0.00001153578,0.0000284632,0.000007128306,0.0007109414,0.00005514019,0.00001246686,0.3477867,0.1959947,0.4551572],"study_design_scores_gemma":[0.001171336,0.0003744389,0.0001243108,0.00001884746,0.000009870576,0.000004625809,0.0001801444,0.8198113,0.0006389715,0.03228803,0.1450619,0.0003161908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006145616,0.00007965519,0.9909656,0.004758885,0.0007622896,0.0003480267,0.00001464004,0.0001778692,0.002278459],"genre_scores_gemma":[0.2737749,0.0000405075,0.7069955,0.004361628,0.0008534031,0.0003814082,0.0003161615,0.00003034789,0.01324617],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8197562,"threshold_uncertainty_score":0.4110745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06969257043282508,"score_gpt":0.3021491390428253,"score_spread":0.2324565686100002,"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."}}