{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004089493,0.000195243,0.0002075108,0.00008910518,0.0000826218,0.0003827534,0.0006209442,0.0001722203,0.00002470138],"category_scores_gemma":[0.00002519014,0.0001600792,0.00007822413,0.00006328537,0.00001540583,0.000262434,0.0009237244,0.0003684268,0.00003514766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009024335,"about_ca_system_score_gemma":0.0001367613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007459858,"about_ca_topic_score_gemma":0.00003799327,"domain_scores_codex":[0.9982207,0.0002044985,0.0002875204,0.0007220959,0.0003378082,0.0002273857],"domain_scores_gemma":[0.9987094,0.00005762158,0.0001465722,0.0009105714,0.0001195573,0.00005630051],"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":[0.0006991632,0.0003447574,0.04964969,0.0006162647,0.0003827958,0.0003018308,0.003909836,0.3483547,0.01867391,0.1050324,0.003642868,0.4683918],"study_design_scores_gemma":[0.0002763285,0.00005658894,0.003384445,0.00005740668,0.000008541273,0.0000186918,0.0000246793,0.9952129,0.0003795586,0.0001373643,0.0002203002,0.0002232181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3904066,0.00002530455,0.6066881,0.001494405,0.0007568676,0.00022577,6.915838e-7,0.0001381531,0.0002641582],"genre_scores_gemma":[0.9610265,0.000001601422,0.03511274,0.0004326784,0.0002404893,0.00002365193,0.00001541904,0.00001079753,0.00313613],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6468582,"threshold_uncertainty_score":0.6527842,"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."}}