{"id":"W4385718182","doi":"10.18653/v1/2023.sigmorphon-1.24","title":"Glossy Bytes: Neural Glossing using Subword Encoding","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Phonology; Encoding (memory); Computer science; Byte; Programming language; Speech recognition; Phonetics; Natural language processing; Artificial intelligence; Linguistics; Cognitive science; Philosophy; Psychology","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":[0.0002931341,0.0009433284,0.0009219865,0.0008225474,0.0004633357,0.001556386,0.001986922,0.0009341598,0.02003779],"category_scores_gemma":[0.001389521,0.0005328018,0.0006418879,0.0009771287,0.0004298931,0.003665376,0.00199092,0.001471842,0.006255622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003753864,"about_ca_system_score_gemma":0.0003922083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002837621,"about_ca_topic_score_gemma":0.005778317,"domain_scores_codex":[0.9998573,0.0000169383,0.00001600353,0.0000547014,0.000035544,0.0000195984],"domain_scores_gemma":[0.9995648,0.0001179234,0.00002397862,0.0001795134,0.00008043593,0.00003335403],"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":[0.0004265511,0.0001143061,0.0006561179,0.0003126178,0.00008977242,0.000204845,0.0001750415,0.006785496,0.05174347,0.01286452,0.04504159,0.8815857],"study_design_scores_gemma":[0.0003372134,0.0005173023,0.003328359,0.0002106927,0.0003567573,0.0006171066,0.0005730414,0.683888,0.1370454,0.09748258,0.07546689,0.0001766456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1912722,0.008749006,0.6726289,0.001535514,0.003965648,0.0002978379,0.007975459,0.07149555,0.04207982],"genre_scores_gemma":[0.5783387,0.003696428,0.3578209,0.0006268919,0.0004948215,0.0002957358,0.01626931,0.005336224,0.03712103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02003779,"threshold_uncertainty_score":0.06703311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04314137413896248,"score_gpt":0.320770194454242,"score_spread":0.2776288203152796,"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."}}