{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002512531,0.0002526215,0.0002888939,0.0002650876,0.0004858501,0.0002382822,0.0002825742,0.00005216626,0.00000124754],"category_scores_gemma":[0.00001084444,0.0001993479,0.00002966285,0.001020344,0.00005076145,0.0005289472,0.0001402426,0.0001367586,0.00000399177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002440318,"about_ca_system_score_gemma":0.0001368497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001491803,"about_ca_topic_score_gemma":0.00005479258,"domain_scores_codex":[0.9980867,0.0000539328,0.0004101851,0.0008178176,0.0003223776,0.0003090106],"domain_scores_gemma":[0.998541,0.0000553549,0.0002572415,0.0007596747,0.0002736028,0.0001131544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004616181,0.0002874571,0.0003229214,0.000104552,0.0003280111,0.000008844508,0.003657534,0.03526955,0.698669,0.2511355,0.0007828176,0.009387603],"study_design_scores_gemma":[0.000514164,0.0001330078,0.00002196907,0.0001631939,0.00003333475,0.00001682171,0.001178459,0.9126217,0.0753367,0.0003658901,0.009218927,0.0003958191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005788852,0.0003411065,0.9898306,0.000701045,0.00002732181,0.002248212,0.00001004046,0.0004699074,0.0005829891],"genre_scores_gemma":[0.4153042,0.00002500428,0.576437,0.0001930774,0.00005168968,0.005849226,0.00002409628,0.00002060132,0.002095073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8773522,"threshold_uncertainty_score":0.8129171,"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."}}