{"id":"W2124618303","doi":"","title":"Substring-Based Transliteration","year":2007,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Transliteration; Substring; Computer science; Margin (machine learning); Artificial intelligence; Word (group theory); Natural language processing; Machine translation; Speech recognition; Programming language; Machine learning; Data structure; Mathematics","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":[0.0008406619,0.0005936558,0.00077991,0.0005918657,0.0005640626,0.001258934,0.001513303,0.0009437546,0.009057875],"category_scores_gemma":[0.004397772,0.0003364872,0.0006686663,0.0009635891,0.0008478089,0.00238298,0.001229785,0.001486846,0.006192189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005366497,"about_ca_system_score_gemma":0.001023985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007096136,"about_ca_topic_score_gemma":0.0008742723,"domain_scores_codex":[0.998674,0.0003185599,0.0001155183,0.00042234,0.000377794,0.00009185897],"domain_scores_gemma":[0.9973017,0.001143154,0.0001532855,0.0007729901,0.0005809411,0.00004805107],"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":[0.0002929316,0.0001809349,0.001156338,0.0008254529,0.0001060288,0.0004762609,0.000805666,0.0549937,0.1950909,0.1380057,0.01461815,0.593448],"study_design_scores_gemma":[0.00005306216,0.0002872222,0.0005512887,0.00006897838,0.00009866714,0.0008506349,0.0001749435,0.5019233,0.3041437,0.1008564,0.09090339,0.00008856576],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00989526,0.0002145862,0.9791346,0.0001927523,0.000113422,0.00006889374,0.0002115368,0.004056973,0.006111972],"genre_scores_gemma":[0.2925997,0.000480064,0.6900888,0.000310421,0.00009645263,0.0001696845,0.001151221,0.001358785,0.01374482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009057875,"threshold_uncertainty_score":0.03030163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01112075728909654,"score_gpt":0.2755006221297466,"score_spread":0.2643798648406501,"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."}}