{"id":"W4282569005","doi":"10.1145/3544103","title":"GDESA: Greedy Diversity Encoder with Self-attention for Search Results Diversification","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Diversification (marketing strategy); Leverage (statistics); Greedy algorithm; Selection (genetic algorithm); Encoder; Ranking (information retrieval); Machine learning; Artificial intelligence; Data mining; Information retrieval; Algorithm; Business","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":[0.0009949347,0.0008179406,0.001009273,0.0009331573,0.0003558718,0.0006490877,0.001373767,0.0009944921,0.001620705],"category_scores_gemma":[0.003014266,0.00036135,0.0005380951,0.0007981936,0.0005941319,0.001405775,0.001323985,0.001163667,0.0007914629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006377927,"about_ca_system_score_gemma":0.001228079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0031585,"about_ca_topic_score_gemma":0.006071839,"domain_scores_codex":[0.9994411,0.0001417895,0.00003059697,0.0001143927,0.0002036655,0.00006845644],"domain_scores_gemma":[0.9988984,0.0005783785,0.00008512131,0.0001388102,0.0002227467,0.00007647782],"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":[0.0004561336,0.0003821985,0.005122396,0.0001961887,0.0001620705,0.0003091148,0.0003300152,0.2460998,0.02586995,0.01309454,0.008391589,0.699586],"study_design_scores_gemma":[0.00003512924,0.00009367888,0.0004590275,0.00001230681,0.00002594922,0.0001114879,0.00001806234,0.9871637,0.00496596,0.005742091,0.00135833,0.00001429432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06418402,0.0016208,0.9273155,0.0003513037,0.0001093497,0.0001348188,0.0002168348,0.00277638,0.003290984],"genre_scores_gemma":[0.7430555,0.0007122,0.2462912,0.0006009414,0.0001496401,0.0002636375,0.0006083215,0.0002405282,0.008078041],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0031585,"threshold_uncertainty_score":0.006280243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03631250601771496,"score_gpt":0.2487990638902549,"score_spread":0.2124865578725399,"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."}}