{"id":"W4391017630","doi":"10.1162/coli_a_00510","title":"Context-aware Transliteration of Romanized South Asian Languages","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Transliteration; Computer science; Romanization; Natural language processing; Context (archaeology); Artificial intelligence; Sentence; Word (group theory); Linguistics; History","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":[0.001427873,0.001698411,0.001161224,0.001040873,0.0009955268,0.001261575,0.001122901,0.0007116284,0.005664816],"category_scores_gemma":[0.005619008,0.0003899137,0.001165528,0.0008862714,0.0004469261,0.00194704,0.002112757,0.001646776,0.006483205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008058232,"about_ca_system_score_gemma":0.001420765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007757365,"about_ca_topic_score_gemma":0.01398284,"domain_scores_codex":[0.9985709,0.0004901661,0.0001405739,0.0005720725,0.0001135139,0.0001127341],"domain_scores_gemma":[0.9970973,0.001161666,0.0001982802,0.000694044,0.0007234067,0.000125327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001799345,0.0003660614,0.01171306,0.002209255,0.0005949676,0.001829821,0.002187291,0.05405498,0.06950298,0.001980131,0.04487806,0.808884],"study_design_scores_gemma":[0.0003247408,0.0007622305,0.01509288,0.0003722511,0.0007037601,0.001688891,0.003320197,0.6984207,0.1945854,0.007834885,0.07663178,0.0002623498],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7515755,0.004817926,0.1586324,0.001304183,0.00158213,0.0005128802,0.01262435,0.05276458,0.01618602],"genre_scores_gemma":[0.8527513,0.0008536799,0.108625,0.0003733602,0.0002031145,0.0002233585,0.02753987,0.001527794,0.007902643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007757365,"threshold_uncertainty_score":0.0189507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01638905617639773,"score_gpt":0.2955521738544959,"score_spread":0.2791631176780982,"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."}}