{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003836234,0.00006035407,0.00006143207,0.000104938,0.00005180012,0.0001706456,0.0001229461,0.00003411234,0.00001084287],"category_scores_gemma":[0.00004863198,0.00005165508,0.00001219633,0.00009511109,0.000008205424,0.003733524,0.0001331702,0.00005123399,0.00009139287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003869916,"about_ca_system_score_gemma":0.00005853135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002051851,"about_ca_topic_score_gemma":0.000002449574,"domain_scores_codex":[0.9994476,0.00004186403,0.0001969108,0.00008723022,0.0001230208,0.000103306],"domain_scores_gemma":[0.9995708,0.00004111955,0.00006501648,0.0002238457,0.00006301094,0.00003620236],"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":[0.0003421273,0.00003803353,0.002488212,0.00009471466,0.00004355733,0.000003817968,0.078803,0.06529557,0.03933854,0.509052,0.0006755625,0.3038249],"study_design_scores_gemma":[0.0002285644,0.00003659881,0.0006813338,0.000005933661,9.171061e-7,0.00001557551,0.0001374578,0.9958743,0.001518567,0.0002843697,0.00113954,0.00007679161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5351071,0.00000392125,0.463821,0.000198995,0.00009943348,0.00007995657,2.682772e-7,0.00003621353,0.0006531561],"genre_scores_gemma":[0.8687382,0.00000358664,0.1305646,0.0005298414,0.00001822036,0.000001436004,0.000001700311,0.000001520736,0.0001407915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9305788,"threshold_uncertainty_score":0.2706715,"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."}}