{"id":"W6948254567","doi":"10.48448/378s-9t86","title":"Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Training set; State (computer science); Language model; Scarcity; Resource (disambiguation)","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":[0.003999695,0.001397907,0.001178838,0.002018278,0.0009467676,0.002647808,0.002172753,0.001214638,0.004462436],"category_scores_gemma":[0.0119434,0.0006910876,0.0009905037,0.001939835,0.001121836,0.008281144,0.004145982,0.002383015,0.002862789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006529718,"about_ca_system_score_gemma":0.001162005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00680446,"about_ca_topic_score_gemma":0.01541767,"domain_scores_codex":[0.9981148,0.0007668339,0.0001536821,0.0006048014,0.0002517959,0.0001080718],"domain_scores_gemma":[0.9950058,0.002496502,0.0003067342,0.001436596,0.0005631202,0.0001912302],"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":[0.0008344762,0.0004229379,0.02921033,0.001175466,0.0005671832,0.001424924,0.002427615,0.08419291,0.02453631,0.01229638,0.02650272,0.8164088],"study_design_scores_gemma":[0.000183273,0.0002700711,0.009232933,0.0003232221,0.0004134988,0.0008005814,0.001337588,0.9091399,0.01933434,0.03539821,0.02340532,0.0001610821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3829805,0.00692757,0.5680516,0.00296826,0.0003766532,0.0003016256,0.003359972,0.01527314,0.01976063],"genre_scores_gemma":[0.8108883,0.0009813539,0.1748163,0.0007367504,0.0001553149,0.0001093877,0.006377338,0.001082371,0.004852898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00680446,"threshold_uncertainty_score":0.02115268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01794667992785194,"score_gpt":0.264371835071692,"score_spread":0.2464251551438401,"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."}}