{"id":"W4385800295","doi":"10.1007/s40747-023-01192-3","title":"An efficient long-text semantic retrieval approach via utilizing presentation learning on short-text","year":2023,"lang":"en","type":"article","venue":"Complex & Intelligent Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Science Foundation of Zhejiang Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Information retrieval; Relevance (law); Ranking (information retrieval); Document retrieval; Query expansion; Matching (statistics); Relevance feedback; Text retrieval; Artificial intelligence; Natural language processing; Image retrieval","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001272982,0.0003327326,0.0004086569,0.0004513318,0.0004196149,0.000558094,0.001297369,0.0001244148,0.00001779027],"category_scores_gemma":[0.00008174111,0.0003251483,0.000143409,0.00110268,0.00005334033,0.0002492917,0.0003148751,0.000392677,0.0006971041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001985872,"about_ca_system_score_gemma":0.00004551191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001123787,"about_ca_topic_score_gemma":0.000004901193,"domain_scores_codex":[0.9959589,0.0005013129,0.000769991,0.00107084,0.001007344,0.0006916726],"domain_scores_gemma":[0.9980367,0.0002290955,0.0001864642,0.001145569,0.000169494,0.0002326713],"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":[0.00002238117,0.0001638566,0.002539399,0.0002225009,0.00004316124,0.00003505533,0.003143653,0.9677018,0.004418017,0.01125436,0.0001777679,0.01027805],"study_design_scores_gemma":[0.0001110032,0.0001571625,0.002351076,0.0001163178,0.00001107523,0.00004058008,0.0009595332,0.9937878,0.001579343,0.00006886625,0.0004865972,0.0003306384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2593571,0.0001299234,0.7364414,0.00004826012,0.001209316,0.0006697804,0.000001202784,0.0007816959,0.001361234],"genre_scores_gemma":[0.9973377,0.00001060469,0.001591569,0.00003382412,0.00034295,0.00003706793,0.0000714831,0.00004451873,0.0005302932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7379805,"threshold_uncertainty_score":0.9999201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1126568722915441,"score_gpt":0.3291043899229319,"score_spread":0.2164475176313878,"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."}}