{"id":"W4308014181","doi":"10.1590/2176-4573e55831","title":"Creating a Large-Scale Audio-Aligned Parsed Corpus of Bilingual Russian Child and Child-Directed Speech (BiRCh): Challenges, Solutions, and Implications for Research","year":2022,"lang":"en","type":"article","venue":"Bakhtiniana Revista de Estudos do Discurso","topic":"Language Development and Disorders","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Parsing; Linguistics; Computer science; Corpus linguistics; Natural language processing; Speech corpus; Artificial intelligence; Speech recognition; Speech synthesis","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.008375403,0.0005691631,0.000810312,0.003783902,0.002344557,0.002576902,0.001369435,0.0009726033,0.005679605],"category_scores_gemma":[0.01404345,0.0006845036,0.0003985735,0.003230194,0.002043416,0.002103386,0.004404255,0.001735029,0.002190873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001657763,"about_ca_system_score_gemma":0.003565491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01476924,"about_ca_topic_score_gemma":0.03307891,"domain_scores_codex":[0.9932721,0.003808325,0.0005777248,0.001234294,0.0007460489,0.000361544],"domain_scores_gemma":[0.9800549,0.01188148,0.001051382,0.002661914,0.003589768,0.0007605858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001977321,0.0014183,0.1086673,0.006735192,0.0004311211,0.007568135,0.08801763,0.009317643,0.2096979,0.02301861,0.06380399,0.4793468],"study_design_scores_gemma":[0.0003845594,0.0006883815,0.5145746,0.001829204,0.0003067376,0.004623936,0.08761942,0.01654656,0.03908794,0.0104239,0.3234558,0.0004589162],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8287924,0.003829675,0.06878503,0.003508514,0.0006125161,0.00177338,0.07296868,0.001816047,0.01791367],"genre_scores_gemma":[0.6652731,0.001644791,0.2076964,0.0005129993,0.0002552207,0.005061381,0.1138993,0.001089958,0.004566794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01476924,"threshold_uncertainty_score":0.04429394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04875747048879389,"score_gpt":0.3515538431071518,"score_spread":0.3027963726183579,"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."}}