{"id":"W2899231639","doi":"10.18653/v1/w19-4103","title":"Augmenting Neural Response Generation with Context-Aware Topical Attention","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Encoder; Context (archaeology); Natural language generation; Attention network; Artificial intelligence; Similarity (geometry); Artificial neural network; Quality (philosophy); Recurrent neural network; Machine learning; Natural 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":[0.001917838,0.00108394,0.0006317846,0.0005874562,0.0002902126,0.0005973279,0.001477182,0.001012674,0.002871804],"category_scores_gemma":[0.007804622,0.0003721015,0.0004991274,0.0004191495,0.0003977356,0.001266916,0.001424212,0.001528606,0.002364727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005812811,"about_ca_system_score_gemma":0.0009013763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003594238,"about_ca_topic_score_gemma":0.006658213,"domain_scores_codex":[0.9989029,0.0005299979,0.00003781628,0.0002916713,0.0001520422,0.00008545421],"domain_scores_gemma":[0.99672,0.002051541,0.0001442926,0.0003817239,0.0005533107,0.0001491393],"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":[0.0009187655,0.0006801501,0.005605113,0.00045071,0.0001687634,0.0003938628,0.0008351433,0.169134,0.097114,0.005799145,0.01611199,0.7027884],"study_design_scores_gemma":[0.00003017573,0.0001073643,0.0004838097,0.00001205087,0.00002486066,0.00006736143,0.00006722948,0.9752864,0.01877411,0.002821845,0.002306112,0.00001859729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1170365,0.000694596,0.8600474,0.0007169306,0.0002726513,0.0002504323,0.001011683,0.01474862,0.005221253],"genre_scores_gemma":[0.7409104,0.000266962,0.2444199,0.0005110024,0.0001522852,0.0003519377,0.002757775,0.0007095331,0.009920207],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003594238,"threshold_uncertainty_score":0.01014262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05465600436238829,"score_gpt":0.2733698889346178,"score_spread":0.2187138845722295,"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."}}