{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002482103,0.003585609,0.001622319,0.001303549,0.001379733,0.002396221,0.002271815,0.002969019,0.01968157],"category_scores_gemma":[0.006847646,0.0008162584,0.001980194,0.001124552,0.0004486976,0.003384734,0.003158057,0.003350369,0.02008031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001245566,"about_ca_system_score_gemma":0.001597969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01214759,"about_ca_topic_score_gemma":0.01902132,"domain_scores_codex":[0.9981837,0.0006081368,0.00008930379,0.0006845713,0.000279482,0.0001548026],"domain_scores_gemma":[0.9982125,0.0006540056,0.00006846625,0.0004600814,0.0004478359,0.0001572476],"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":[0.001306293,0.0008811392,0.00603926,0.0008286353,0.0003695637,0.0007974647,0.0003061317,0.01768247,0.02379847,0.00332031,0.3926958,0.5519747],"study_design_scores_gemma":[0.0005588975,0.0003942266,0.007033995,0.00009336765,0.0001399687,0.0004430336,0.000377711,0.8680361,0.02195626,0.01326761,0.0875783,0.0001204778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2030324,0.006036698,0.4851943,0.005453721,0.004469081,0.002452552,0.08818947,0.156379,0.04879282],"genre_scores_gemma":[0.3783895,0.000924278,0.3963283,0.001922288,0.0007464373,0.002232062,0.1836467,0.00487274,0.03093781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01968157,"threshold_uncertainty_score":0.06584144,"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."}}