{"id":"W4387183694","doi":"10.1111/coin.12603","title":"A semantically enhanced text retrieval framework with abstractive summarization","year":2023,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Barrie Urology Group; York University","funders":"China Scholarship Council; Natural Science Foundation of Hubei Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Hubei Provincial Department of Education","keywords":"Computer science; Automatic summarization; Natural language processing; Artificial intelligence; Question answering; Encoder; Language model; Information retrieval; Generative grammar; Transformer; Semantics (computer science); Sequence (biology); Programming language","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":[0.00104607,0.0008896107,0.0008876438,0.002089759,0.0003928128,0.001252827,0.001322908,0.0008495528,0.003778058],"category_scores_gemma":[0.002497177,0.0002975108,0.0009273479,0.00158688,0.0004681732,0.00229054,0.001090232,0.001115568,0.00226182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006817575,"about_ca_system_score_gemma":0.0009292898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002880962,"about_ca_topic_score_gemma":0.003750714,"domain_scores_codex":[0.9992554,0.0002870746,0.00005619208,0.0001409619,0.0001845603,0.00007578674],"domain_scores_gemma":[0.9993623,0.0002290426,0.0000799511,0.0001108977,0.0001813199,0.00003653408],"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":[0.0004417252,0.000344204,0.0007664392,0.0005843203,0.0001554721,0.0004355703,0.0005014124,0.1837664,0.04491758,0.06160751,0.02097801,0.6855013],"study_design_scores_gemma":[0.00004129252,0.0001462093,0.0001960172,0.00002002946,0.00006986116,0.0001052417,0.00007509245,0.9583941,0.009748288,0.02472896,0.006444154,0.0000306466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01468157,0.0008549489,0.9764495,0.0003400565,0.00008233498,0.0001211829,0.0004764104,0.00473367,0.002260161],"genre_scores_gemma":[0.4904183,0.0009349749,0.491527,0.0003722913,0.0003598233,0.0002844992,0.004092832,0.0007015927,0.0113086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003778058,"threshold_uncertainty_score":0.01263893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02991899628109718,"score_gpt":0.299368928543697,"score_spread":0.2694499322625998,"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."}}