{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003369926,0.001894575,0.001558131,0.002098009,0.001185031,0.001671175,0.003500605,0.001675275,0.004200251],"category_scores_gemma":[0.01039242,0.0008110997,0.001498962,0.001241298,0.001253297,0.005236235,0.003308765,0.004077962,0.002902915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001199448,"about_ca_system_score_gemma":0.001596332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007999845,"about_ca_topic_score_gemma":0.01397249,"domain_scores_codex":[0.997799,0.0007867292,0.000115027,0.0007536836,0.000338318,0.0002073262],"domain_scores_gemma":[0.9942504,0.003611272,0.0001731635,0.001018603,0.0006510637,0.0002954456],"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":[0.001014467,0.001149017,0.004749223,0.0006177799,0.0002279736,0.0002627265,0.001174629,0.071446,0.02371971,0.01119653,0.02118666,0.8632553],"study_design_scores_gemma":[0.0000544069,0.0001876346,0.0007676404,0.00003019609,0.00004321729,0.0001229583,0.0003273024,0.9689511,0.007977308,0.01797203,0.003521867,0.00004427601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05243711,0.00120342,0.9295036,0.0005280992,0.0002114704,0.0002027416,0.000493144,0.01322211,0.002198261],"genre_scores_gemma":[0.4400979,0.0004006558,0.5452598,0.0007539837,0.000257269,0.0003821468,0.004521189,0.001280341,0.007046743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007999845,"threshold_uncertainty_score":0.01782209,"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."}}