{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001339418,0.00007734253,0.0000872089,0.00005773615,0.000379933,0.00006732014,0.0007907249,0.00003661361,0.000006581245],"category_scores_gemma":[0.00001331828,0.00007171665,0.00004995148,0.0001947666,0.0000122266,0.0005343717,0.001774566,0.0000582332,0.0000183293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002247684,"about_ca_system_score_gemma":0.00002555323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001611119,"about_ca_topic_score_gemma":0.00002554845,"domain_scores_codex":[0.9991344,0.00001151125,0.0001059457,0.0003197723,0.0001578766,0.000270553],"domain_scores_gemma":[0.9994311,0.00006795673,0.00002740979,0.0003598378,0.00005617867,0.00005745652],"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":[0.00001192611,0.00004865634,0.009956537,0.000257289,0.00003047749,0.00008718063,0.007755782,0.1266311,0.0006518638,0.4178328,0.002472495,0.4342639],"study_design_scores_gemma":[0.0001615059,0.00001971536,0.0002610644,0.0000029471,0.000001935703,0.0000017877,0.00003962817,0.9795502,0.000176227,0.01963441,0.00005601735,0.00009457485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1087856,0.000007519347,0.8889071,0.0008635597,0.0003521959,0.0001620468,0.000001470351,0.0004406618,0.0004797727],"genre_scores_gemma":[0.9770704,9.52795e-7,0.02022701,0.0002943707,0.00005837266,0.00001354389,0.000001256832,0.000004055119,0.002330062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8686801,"threshold_uncertainty_score":0.292452,"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."}}