{"id":"W4367189822","doi":"10.48550/arxiv.2304.13292","title":"Zero-Shot Slot and Intent Detection in Low-Resource Languages","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Compute Canada; Advanced Micro Devices","keywords":"Computer science; Dialog box; Margin (machine learning); Task (project management); Zero (linguistics); Encoder; Generalization; Natural language understanding; Natural language processing; Baseline (sea); Language model; Natural language; Artificial intelligence; Resource (disambiguation); Speech recognition; Machine learning; Linguistics; World Wide Web; Mathematics; Engineering","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":[0.002774847,0.001447555,0.001174582,0.0008303282,0.0007976974,0.001751307,0.001892914,0.001722879,0.003614921],"category_scores_gemma":[0.01046113,0.0005283633,0.001022078,0.0005408569,0.0009987287,0.004335926,0.002798754,0.002697744,0.002601963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000608567,"about_ca_system_score_gemma":0.001021892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003589715,"about_ca_topic_score_gemma":0.005097184,"domain_scores_codex":[0.9978468,0.000913851,0.00008591334,0.000672696,0.0002665186,0.0002141813],"domain_scores_gemma":[0.9940037,0.004028366,0.0002518363,0.0009477971,0.0005114818,0.0002568006],"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":[0.002981573,0.001091666,0.0131309,0.001208378,0.0002154419,0.001410575,0.003086446,0.07907279,0.1016229,0.01720561,0.02889598,0.7500778],"study_design_scores_gemma":[0.0000839674,0.0004540157,0.004381146,0.00006138085,0.00005121456,0.0006877953,0.0008625303,0.920922,0.03519579,0.03002109,0.00716171,0.0001173663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.405229,0.001407327,0.5701142,0.0008105463,0.0003249584,0.0002035809,0.002047024,0.01320845,0.006654829],"genre_scores_gemma":[0.8307395,0.0002031,0.1587956,0.0003271287,0.0001109853,0.0001351309,0.003863244,0.0006266317,0.005198673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003614921,"threshold_uncertainty_score":0.01467496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05611880373767168,"score_gpt":0.2142529616680975,"score_spread":0.1581341579304259,"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."}}