{"id":"W2972603547","doi":"10.18653/v1/w19-4115","title":"Relevant and Informative Response Generation using Pointwise Mutual Information","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Japan Society for the Promotion of Science; Microsoft Research Asia; Microsoft Research","keywords":"Pointwise; Pointwise mutual information; Computer science; Utterance; Sequence (biology); Mutual information; Simple (philosophy); Artificial intelligence; Machine learning; Mathematics","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":[0.002910602,0.001057153,0.0007656092,0.0008489043,0.0003991764,0.0007786731,0.001269941,0.001338679,0.002833737],"category_scores_gemma":[0.01188951,0.000481691,0.0007278607,0.0004591339,0.0008828667,0.001958292,0.001353211,0.00142364,0.0009885314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006643447,"about_ca_system_score_gemma":0.0008764919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00124034,"about_ca_topic_score_gemma":0.001861322,"domain_scores_codex":[0.9974069,0.001570396,0.0000850908,0.0004849128,0.0003319072,0.0001207756],"domain_scores_gemma":[0.9935214,0.004839227,0.0003438189,0.0004897292,0.000610659,0.000195217],"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":[0.001228944,0.000498433,0.004392001,0.0004524371,0.0002511989,0.0004133506,0.001416288,0.4902357,0.05416591,0.03473025,0.005958654,0.4062568],"study_design_scores_gemma":[0.00002608892,0.0000969063,0.0002907157,0.00001089109,0.00002151028,0.00006819648,0.00002795051,0.9823114,0.005803017,0.0107465,0.0005768476,0.00002004219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06295878,0.0002205855,0.9312987,0.0004472435,0.00005080408,0.0001888872,0.0001178258,0.001723311,0.00299392],"genre_scores_gemma":[0.8410605,0.0001378048,0.1539594,0.0002448175,0.00006101776,0.0004215919,0.0002713703,0.0002626766,0.003580793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002910602,"threshold_uncertainty_score":0.0153929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02158601777901397,"score_gpt":0.2390819984208023,"score_spread":0.2174959806417884,"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."}}