{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001024086,0.0001387451,0.0001349638,0.0004948316,0.002592865,0.0003028278,0.0009481208,0.00005425573,0.00001858937],"category_scores_gemma":[0.00001540317,0.0001278814,0.0000902383,0.0008156362,0.00002545666,0.003846733,0.00009835936,0.0002520356,0.0001225578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003847255,"about_ca_system_score_gemma":0.0001226954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001990293,"about_ca_topic_score_gemma":0.000003695216,"domain_scores_codex":[0.9978534,0.0001135627,0.0004771807,0.0001937643,0.001088667,0.0002734027],"domain_scores_gemma":[0.9983627,0.0001320579,0.0002270352,0.0006503335,0.000525746,0.0001021611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00476841,0.00193647,0.002763328,0.001190127,0.0007313012,0.00001170352,0.1563346,0.5508053,0.0002725673,0.06576147,0.01100996,0.2044148],"study_design_scores_gemma":[0.01625185,0.00488313,0.02007701,0.0001018433,0.0001891671,0.0002347813,0.03447379,0.7549126,0.00147853,0.000220901,0.1654293,0.001747098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01562226,0.000003106456,0.9801015,0.0007738593,0.0006001431,0.001294069,0.0003988452,0.0003391716,0.0008670685],"genre_scores_gemma":[0.9924127,0.000005732815,0.006392853,0.0001494087,0.00001754014,0.0003291035,0.0002147774,0.000005168625,0.0004726469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9767905,"threshold_uncertainty_score":0.9987056,"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."}}