{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001822414,0.0001072844,0.0001515844,0.0001861834,0.00008181569,0.00008417305,0.0004261225,0.00006021512,0.000005606549],"category_scores_gemma":[0.0006728086,0.0001044454,0.00005173793,0.0005242029,0.00004296631,0.000060973,0.00007797809,0.0001051529,0.00002366907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001892657,"about_ca_system_score_gemma":0.00008573226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005438433,"about_ca_topic_score_gemma":0.000002558329,"domain_scores_codex":[0.9990222,0.00004061929,0.0002682708,0.0002195209,0.0003052021,0.0001441372],"domain_scores_gemma":[0.9989225,0.0001683295,0.0001253149,0.0001848515,0.0005553298,0.00004372722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001068874,0.00003803947,0.0003837764,0.0001194365,0.00002585746,0.00006306955,0.005425244,0.001840634,0.000202788,0.9711305,0.001620704,0.01913924],"study_design_scores_gemma":[0.0007829254,0.0001264275,0.002233902,0.0002047125,0.00002292748,0.00001279803,0.0003498165,0.5554255,0.004640022,0.4329648,0.002783504,0.0004527495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001575789,0.0002906228,0.9956532,0.0003075687,0.0002912522,0.000122298,0.00003795369,0.0008908935,0.0008304857],"genre_scores_gemma":[0.755289,9.464952e-7,0.2442854,0.0001259693,0.0001272373,0.000004186276,0.00009643649,0.000008684204,0.00006214235],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7537133,"threshold_uncertainty_score":0.4259161,"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."}}