{"id":"W4415422573","doi":"10.1016/j.eswa.2025.130088","title":"DGSEP: Dual-stage generative model with sequence-oriented labeling and element-to-tuple prompting improves aspect sentiment triplet extraction","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Sichuan Province Science and Technology Support Program; Key Research and Development Program of Sichuan Province; Chengdu Science and Technology Bureau; Department of Science and Technology of Sichuan Province; National Natural Science Foundation of China","keywords":"Fuse (electrical); Generative grammar; Generative model; Sequence (biology); Task (project management); Sentiment analysis","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":[0.001069282,0.001577517,0.000951231,0.001223198,0.0007370836,0.001517908,0.00201975,0.001729746,0.008648429],"category_scores_gemma":[0.00288965,0.0009600632,0.001946438,0.001128084,0.0005535012,0.00234308,0.002244402,0.002922758,0.00606732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006591034,"about_ca_system_score_gemma":0.001874743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007068081,"about_ca_topic_score_gemma":0.01688471,"domain_scores_codex":[0.9992315,0.000185855,0.00004248413,0.0003083419,0.0001470345,0.00008484006],"domain_scores_gemma":[0.9986131,0.0006521457,0.0000581398,0.0003237806,0.0002792465,0.0000735815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001134931,0.0005043329,0.00573816,0.0005623579,0.0002548552,0.0008282618,0.0008484871,0.09650544,0.05852775,0.02124057,0.05593546,0.7579195],"study_design_scores_gemma":[0.00004192774,0.00005711059,0.000635336,0.00002351588,0.00006366312,0.0001178605,0.0000638951,0.9650258,0.01075101,0.01542466,0.007764675,0.00003043099],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01786525,0.0002893348,0.9547887,0.0003424651,0.0002394179,0.000209483,0.001692491,0.02142648,0.003146211],"genre_scores_gemma":[0.3076178,0.0002630463,0.6644517,0.0006992757,0.0001903865,0.0003633692,0.01062396,0.004019457,0.01177098],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008648429,"threshold_uncertainty_score":0.02893186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01813607590511513,"score_gpt":0.3202483510847026,"score_spread":0.3021122751795874,"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."}}