{"id":"W4403557996","doi":"10.1016/j.asoc.2024.112338","title":"Few-shot intent detection with mutual information and contrastive learning","year":2024,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Sichuan Province Science and Technology Support Program; National Natural Science Foundation of China","keywords":"Computer science; Mutual information; Shot (pellet); Artificial intelligence; Pattern recognition (psychology); Chemistry","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":[0.0004592658,0.0001679774,0.0001524315,0.000159009,0.0003527248,0.0005539759,0.0002093473,0.00006224387,0.000002433831],"category_scores_gemma":[0.00008684172,0.000149007,0.00002341098,0.0004003032,0.00005934991,0.0006945658,0.000304297,0.0005944159,0.00003814294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000757509,"about_ca_system_score_gemma":0.00004725835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002042639,"about_ca_topic_score_gemma":0.000003576383,"domain_scores_codex":[0.9988979,0.000045564,0.0002327585,0.0003151553,0.0002417661,0.0002668468],"domain_scores_gemma":[0.9992538,0.0003954663,0.0001040405,0.0001241235,0.00005836092,0.00006417013],"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":[0.00002764267,0.000005792535,0.000312793,0.00006122208,0.00004521674,0.00001049038,0.007050625,0.1852186,0.0007952454,0.02963852,0.000009719917,0.7768242],"study_design_scores_gemma":[0.0002982093,0.00008485658,0.0008178391,0.00007997704,0.00001202357,0.0000549012,0.0006388122,0.9956052,0.0004198854,0.0003808947,0.001406079,0.0002013195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05731045,0.00005082241,0.939403,0.00008128503,0.0002708292,0.0001694445,1.705946e-7,0.0007385632,0.001975455],"genre_scores_gemma":[0.9737264,0.000001746552,0.02602667,0.0001075274,0.0001011094,0.000006636164,0.000003699027,0.00001267755,0.00001354545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9164159,"threshold_uncertainty_score":0.6076328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006481579155710362,"score_gpt":0.2198817190138898,"score_spread":0.2134001398581794,"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."}}