{"id":"W3167335398","doi":"10.18653/v1/2021.sigtyp-1.11","title":"SIGTYP 2021 Shared Task: Robust Spoken Language Identification","year":2021,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Typology; Computer science; Identification (biology); Task (project management); Natural language processing; Artificial intelligence; Linguistics; History; Engineering; Philosophy; Biology; Archaeology","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":[0.00806047,0.004347791,0.003417028,0.002669462,0.003293266,0.004705799,0.004976033,0.006420907,0.03478792],"category_scores_gemma":[0.01667705,0.001371627,0.001596691,0.001817201,0.00134138,0.005589299,0.009635868,0.004239268,0.06311616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001469906,"about_ca_system_score_gemma":0.004830746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02137133,"about_ca_topic_score_gemma":0.02849227,"domain_scores_codex":[0.9916254,0.003973862,0.0004774915,0.001707185,0.001483422,0.0007326726],"domain_scores_gemma":[0.9864291,0.004824207,0.0003425473,0.004102099,0.003188092,0.001113891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001467084,0.0004750159,0.00138626,0.001085431,0.0003058113,0.0006564936,0.0004404176,0.002629554,0.01331139,0.001263477,0.8022565,0.1747226],"study_design_scores_gemma":[0.004311866,0.001817291,0.0233267,0.0006460589,0.0006358959,0.002604742,0.005624251,0.244571,0.07541971,0.02140697,0.6186255,0.001009948],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.08914442,0.006062885,0.216903,0.00554329,0.009055163,0.003153564,0.3908443,0.2282382,0.05105521],"genre_scores_gemma":[0.1202432,0.0005918354,0.1250277,0.001286087,0.0007732366,0.003729747,0.698807,0.00891549,0.04062569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03478792,"threshold_uncertainty_score":0.1163772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01274989262124065,"score_gpt":0.2627833683118665,"score_spread":0.2500334756906258,"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."}}