{"id":"W4389523844","doi":"10.18653/v1/2023.findings-emnlp.780","title":"Efficient Cross-Task Prompt Tuning for Few-Shot Conversational Emotion Recognition","year":2023,"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":"BC Research (Canada)","funders":"Nanyang Technological University; National Research Foundation Singapore; National Research Foundation","keywords":"Computer science; Conversation; Task (project management); Shot (pellet); Curse of dimensionality; Artificial intelligence; Machine learning; Speech recognition; Human–computer interaction","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":[0.0005257628,0.00008128353,0.00009307209,0.0001978734,0.0002301046,0.0002508349,0.0001986303,0.00003699443,0.0001467491],"category_scores_gemma":[0.00005311926,0.00007581225,0.00009878105,0.0005576077,0.00001959269,0.0001685738,0.00007550358,0.00003845396,0.0004104236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003129564,"about_ca_system_score_gemma":0.00003098312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005861726,"about_ca_topic_score_gemma":0.000001017917,"domain_scores_codex":[0.9989735,0.00002349192,0.0002125232,0.0003233862,0.0002622576,0.0002048419],"domain_scores_gemma":[0.9994254,0.0001221625,0.00008340506,0.0001596957,0.0001611457,0.00004824604],"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":[0.0001750773,0.001035522,0.04001636,0.000388572,0.0008827604,0.00003001809,0.01846491,0.1613389,0.08184835,0.2082953,0.0950074,0.3925168],"study_design_scores_gemma":[0.0004029599,0.00003521108,0.00750935,0.00001550833,0.000006870707,0.000001149511,0.0001156396,0.9884045,0.001590578,0.0009569573,0.0008447518,0.0001165158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2479618,0.000007140564,0.7487389,0.0009295595,0.0005518247,0.0002275068,0.000005459113,0.0003041224,0.00127372],"genre_scores_gemma":[0.9741093,0.000002551085,0.02361546,0.0002261032,0.000143614,0.00004167698,0.0002552595,0.000007942918,0.001598088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8270656,"threshold_uncertainty_score":0.5275301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07862116703193545,"score_gpt":0.3224445381416058,"score_spread":0.2438233711096703,"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."}}