{"id":"W4407974294","doi":"10.1145/3720542","title":"A Hybrid Statistical and Rule-based Approach to Extremely Low-resource Machine Transliteration","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Transliteration; Computer science; Artificial intelligence; Rule-based system; Resource (disambiguation); Natural language processing; Machine learning; Data mining","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":[0.002475121,0.001056825,0.001463469,0.00286664,0.000791579,0.002559128,0.003481961,0.00132119,0.002618691],"category_scores_gemma":[0.01041806,0.0005567497,0.001084108,0.00408518,0.001506448,0.003204772,0.002308918,0.002456186,0.004934191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007072099,"about_ca_system_score_gemma":0.002408307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003554757,"about_ca_topic_score_gemma":0.005940469,"domain_scores_codex":[0.9959306,0.0009311204,0.0003910281,0.001056391,0.00153926,0.0001516016],"domain_scores_gemma":[0.9926679,0.002721588,0.0003603891,0.002482222,0.001636703,0.000131288],"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":[0.0002724708,0.0003201584,0.002150466,0.0002292376,0.0001397855,0.0003535645,0.0003051067,0.08076621,0.02549945,0.01529099,0.01020218,0.8644704],"study_design_scores_gemma":[0.00006544108,0.0001516245,0.0006499008,0.00002460691,0.00005231472,0.0004253309,0.0000946471,0.9344708,0.02602411,0.02658449,0.01140323,0.00005351036],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01173723,0.0004391626,0.9760543,0.0003213295,0.00008959971,0.000115153,0.000444331,0.008870427,0.001928429],"genre_scores_gemma":[0.14058,0.000358186,0.8498511,0.0004808767,0.0001713339,0.0003271618,0.003018168,0.0006744171,0.00453875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003554757,"threshold_uncertainty_score":0.0130899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005748411853017093,"score_gpt":0.2307737058908388,"score_spread":0.2250252940378217,"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."}}