{"id":"W4385571773","doi":"10.18653/v1/2023.acl-short.145","title":"Diversity-Aware Coherence Loss for Improving Neural Topic Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of the Fraser Valley; University of British Columbia","funders":"","keywords":"Computer science; Coherence (philosophical gambling strategy); Diversity (politics); Artificial neural network; Artificial intelligence; Mathematics; Statistics","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":[0.00338474,0.001279131,0.00165164,0.001720126,0.000865915,0.00129793,0.002123234,0.001478704,0.00239809],"category_scores_gemma":[0.01167505,0.0006419986,0.0008454271,0.002067,0.0006229292,0.004132661,0.002458971,0.002632097,0.001497194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008936057,"about_ca_system_score_gemma":0.0011333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004836839,"about_ca_topic_score_gemma":0.009195887,"domain_scores_codex":[0.9986998,0.0005517187,0.00006927719,0.000316765,0.000235997,0.0001264923],"domain_scores_gemma":[0.9958365,0.002717317,0.0001738783,0.0005233278,0.0005792418,0.0001697315],"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":[0.001034999,0.0003406583,0.003792005,0.0003502866,0.0004479525,0.0001141554,0.0004933863,0.2445167,0.0132996,0.01403,0.03573394,0.6858463],"study_design_scores_gemma":[0.00007582062,0.0001281745,0.0006361916,0.0000210146,0.00008798306,0.00004788846,0.00005182266,0.9800827,0.002423037,0.01430062,0.002127315,0.00001745786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07753664,0.00836073,0.9048326,0.001156927,0.0003315293,0.00009465052,0.0007909678,0.003407461,0.003488498],"genre_scores_gemma":[0.7688063,0.002483322,0.2144408,0.0007349073,0.001246992,0.0002759644,0.004593563,0.0008647515,0.006553475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004836839,"threshold_uncertainty_score":0.01790041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06884440324724243,"score_gpt":0.2589434678044306,"score_spread":0.1900990645571881,"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."}}