{"id":"W4404783983","doi":"10.18653/v1/2024.emnlp-industry.68","title":"A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasks","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Computer science; Scope (computer science); Sentence; Transformer; Artificial intelligence; Natural language processing; Engineering; Electrical engineering; Programming language; Voltage","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002563236,0.001442469,0.0008630226,0.001536461,0.0004564982,0.001411967,0.001499132,0.0009621392,0.003054308],"category_scores_gemma":[0.01060544,0.0005108962,0.0008138678,0.0007215532,0.0007606445,0.00457477,0.002054742,0.002428325,0.002495154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006366182,"about_ca_system_score_gemma":0.00132665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001781009,"about_ca_topic_score_gemma":0.003161275,"domain_scores_codex":[0.9978489,0.0005502533,0.0002255964,0.0005798209,0.0006596601,0.0001357428],"domain_scores_gemma":[0.9954743,0.001442567,0.0003998669,0.00113214,0.001334207,0.0002168289],"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":[0.0006557112,0.0006723251,0.005517839,0.0002496527,0.0001283002,0.0001608291,0.0004253047,0.02356282,0.09298137,0.005028963,0.0104361,0.8601808],"study_design_scores_gemma":[0.00008049019,0.0006950927,0.002495764,0.0000382489,0.00009240998,0.0005452196,0.0001816298,0.9187397,0.06074433,0.009180708,0.00714832,0.00005797187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04803406,0.0005717368,0.9346167,0.0003578631,0.0001865996,0.0002725296,0.0003807742,0.0135797,0.002000007],"genre_scores_gemma":[0.50135,0.0002973186,0.4890442,0.0006433529,0.0002233537,0.000293631,0.001906848,0.001027943,0.00521342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003054308,"threshold_uncertainty_score":0.01355588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06658125175465925,"score_gpt":0.3089258718649948,"score_spread":0.2423446201103356,"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."}}