{"id":"W4400524689","doi":"10.1145/3626772.3657894","title":"LADy 💃: A Benchmark Toolkit for Latent Aspect Detection Enriched with Backtranslation Augmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Universitas Brawijaya; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Cartography; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004933793,0.003433701,0.001103583,0.005465849,0.001136697,0.00350712,0.003771527,0.001658068,0.01246261],"category_scores_gemma":[0.02371833,0.001559653,0.00286426,0.004467826,0.0007830081,0.005003654,0.003438393,0.002280241,0.01710379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00161846,"about_ca_system_score_gemma":0.003218904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01540598,"about_ca_topic_score_gemma":0.03027849,"domain_scores_codex":[0.9957474,0.001289022,0.0005200338,0.001043205,0.001091487,0.0003088783],"domain_scores_gemma":[0.9925123,0.003457775,0.0004474829,0.002015178,0.001317966,0.0002492849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006738711,0.0002782411,0.008041078,0.00487358,0.0007366186,0.0005153207,0.0008713715,0.02505039,0.01075125,0.008773101,0.6252075,0.3142276],"study_design_scores_gemma":[0.0004456612,0.0003476856,0.009899788,0.0006336442,0.0002880994,0.001411515,0.0006796474,0.4148302,0.03736584,0.02680743,0.5069341,0.0003563746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.02244849,0.004893254,0.3206362,0.001180813,0.0008828798,0.001044547,0.1089921,0.5238666,0.01605511],"genre_scores_gemma":[0.09858629,0.002139336,0.4578861,0.001052769,0.0001625968,0.002266719,0.3904091,0.0359537,0.01154335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01540598,"threshold_uncertainty_score":0.0416916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02082889209842393,"score_gpt":0.2527016672092294,"score_spread":0.2318727751108055,"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."}}