{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002654318,0.002149066,0.001766585,0.0006837467,0.0006807568,0.001032523,0.002086711,0.001577119,0.004355036],"category_scores_gemma":[0.008967638,0.0006429943,0.001057019,0.0006684904,0.0007377435,0.002435742,0.002587657,0.002935984,0.002712655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006702342,"about_ca_system_score_gemma":0.001678613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003315771,"about_ca_topic_score_gemma":0.004809118,"domain_scores_codex":[0.9982333,0.0004342885,0.00009218466,0.0007513065,0.0002627021,0.0002260672],"domain_scores_gemma":[0.9982538,0.0007638886,0.00009023408,0.0002989335,0.0004258056,0.0001674559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001247869,0.0009261689,0.002902905,0.00041121,0.0002147453,0.0002668579,0.000434893,0.1448115,0.05183914,0.002914655,0.01561229,0.7784179],"study_design_scores_gemma":[0.00006501229,0.0001818768,0.001111066,0.00001302025,0.00003097071,0.00008773884,0.000101147,0.9852786,0.007670532,0.003826744,0.001602673,0.00003066389],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04914358,0.001196684,0.9377671,0.0002426081,0.0002818603,0.0002157859,0.0002350559,0.008602376,0.002314892],"genre_scores_gemma":[0.6564114,0.0004075558,0.3318589,0.0008229424,0.0002445264,0.0007860941,0.002340203,0.001117957,0.006010503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004355036,"threshold_uncertainty_score":0.01456904,"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."}}