{"id":"W4385571765","doi":"10.18653/v1/2023.acl-industry.71","title":"Exploring Zero and Few-shot Techniques for Intent Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Minnow Environmental (Canada)","funders":"","keywords":"Computer science; Constraint (computer-aided design); Resource (disambiguation); Zero (linguistics); Adaptation (eye); Shot (pellet); Limited resources; Face (sociological concept); Language model; Sample (material); Artificial intelligence; Machine learning; Mathematics; Linguistics; Statistics","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":[0.0001925502,0.00004178371,0.00004678413,0.00007053011,0.00004950102,0.00006447187,0.0001796434,0.00001580039,9.182904e-7],"category_scores_gemma":[0.00002132392,0.00003648184,0.00001509493,0.0001239734,0.000007238257,0.0003273413,0.000117686,0.00002758178,0.000007466278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001443228,"about_ca_system_score_gemma":0.000007495624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001049871,"about_ca_topic_score_gemma":0.000001894915,"domain_scores_codex":[0.9995323,0.000005990308,0.00009273642,0.0001956713,0.00006584284,0.0001074788],"domain_scores_gemma":[0.9996692,0.00004363646,0.00001713934,0.0002107248,0.00003247273,0.00002684296],"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":[0.000001453407,0.000007041391,0.0003177981,0.00002214586,0.000003726572,7.00038e-7,0.0005944708,0.00001425501,0.01064872,0.4815439,0.001011122,0.5058347],"study_design_scores_gemma":[0.00009896757,0.00004694982,0.00268031,0.00002517948,0.000002104196,0.000002712807,0.0001800997,0.9272424,0.03382144,0.02686713,0.008889501,0.0001432033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02288097,0.000005975369,0.9729727,0.002191247,0.0001233077,0.0001433914,2.029334e-7,0.0006239145,0.00105829],"genre_scores_gemma":[0.8241776,0.00002926773,0.175079,0.0001093172,0.00003196896,0.0001735687,9.49018e-7,0.000003968486,0.000394363],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9272282,"threshold_uncertainty_score":0.1487686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4411939191832756,"score_gpt":0.3375341698411399,"score_spread":0.1036597493421357,"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."}}