{"id":"W4401042968","doi":"10.18653/v1/2024.semeval-1.164","title":"PetKaz at SemEval-2024 Task 3: Advancing Emotion Classification with an LLM for Emotion-Cause Pair Extraction in Conversations","year":2024,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"SemEval; Task (project management); Computer science; Natural language processing; Artificial intelligence; Extraction (chemistry); Emotion detection; Speech recognition; Emotion recognition; Chromatography; Engineering","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":[0.0005107979,0.0001322203,0.0001246836,0.0003837076,0.0001768978,0.0003137553,0.0001676075,0.00005680314,0.0001529917],"category_scores_gemma":[0.00002249031,0.000113196,0.00007048928,0.0007385454,0.00001854124,0.001756505,0.00003538434,0.00009266741,0.00007416499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002590682,"about_ca_system_score_gemma":0.00007143115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003203934,"about_ca_topic_score_gemma":0.000299408,"domain_scores_codex":[0.998622,0.00006521281,0.0003020755,0.0005418306,0.0002545387,0.0002143266],"domain_scores_gemma":[0.9992731,0.0001458245,0.00008535346,0.0003215149,0.0001016628,0.00007252941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000269787,0.001965405,0.09282219,0.0007770337,0.0009023853,0.00007465525,0.02792004,0.03006224,0.1040613,0.3916553,0.04191621,0.3075735],"study_design_scores_gemma":[0.0002945481,0.0001554874,0.01250003,0.00007823612,0.00003866864,0.000009700243,0.00100912,0.9790945,0.0009881918,0.0004678004,0.005190345,0.0001733443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.132493,0.00004851974,0.8634198,0.002315141,0.0005984293,0.000294584,0.000002832875,0.0002411793,0.0005865265],"genre_scores_gemma":[0.9573641,0.00002611953,0.03812782,0.00009714094,0.0001304462,0.00005227157,0.0001127079,0.0000154219,0.00407397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9490323,"threshold_uncertainty_score":0.4616001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04026484820025493,"score_gpt":0.3169309115703094,"score_spread":0.2766660633700544,"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."}}