{"id":"W4402683397","doi":"10.18653/v1/2024.sighan-1.13","title":"ZZU-NLP at SIGHAN-2024 dimABSA Task: Aspect-Based Sentiment Analysis with Coarse-to-Fine In-context Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Task (project management); Natural language processing; Context (archaeology); Sentiment analysis; Engineering; History","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005372812,0.0003106669,0.0004989174,0.001449733,0.0001706393,0.0006982365,0.0005521714,0.000059902,0.001726922],"category_scores_gemma":[0.0000173665,0.0002372013,0.0003219208,0.005133587,0.00003474055,0.0003036032,0.0003359326,0.0002453174,0.000859854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002363397,"about_ca_system_score_gemma":0.00008945829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001994253,"about_ca_topic_score_gemma":0.001681894,"domain_scores_codex":[0.9971766,0.0001122767,0.0004793227,0.001047279,0.0006793131,0.0005051396],"domain_scores_gemma":[0.9988341,0.0002228333,0.00008758676,0.0005846111,0.00007214196,0.0001987432],"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":[0.0002373168,0.0009609926,0.2147967,0.0002086818,0.008950163,0.001921239,0.009417826,0.5464157,0.01141223,0.0404992,0.03013221,0.1350477],"study_design_scores_gemma":[0.0004683154,0.0002461013,0.002085134,0.0001063364,0.0003547784,0.000003716378,0.0002558282,0.9721915,0.004525986,0.00002789445,0.01928518,0.0004492169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2400977,0.0009893485,0.7420566,0.003822346,0.0005962009,0.0003724987,0.000004099823,0.0005847483,0.01147646],"genre_scores_gemma":[0.9665488,0.000004957951,0.009713266,0.0003765215,0.00006394587,0.00002868333,0.00002639768,0.00002198512,0.02321544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7323433,"threshold_uncertainty_score":0.9999181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01123320250382557,"score_gpt":0.2495884170763642,"score_spread":0.2383552145725386,"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."}}