{"id":"W2293438896","doi":"10.3115/v1/n15-1095","title":"Joint Generation of Transliterations from Multiple Representations","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Transliteration; Computer science; Spelling; Natural language processing; Artificial intelligence; Pronunciation; Joint (building); Lexicon; Speech recognition; Machine translation; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001021282,0.00004710312,0.00006742616,0.00006019161,0.00003244215,0.00007522732,0.0002269782,0.00002921346,0.00001153874],"category_scores_gemma":[0.0001102482,0.00003942713,0.00002545006,0.0001833433,0.00001558802,0.0005521024,0.00004144623,0.00004260528,0.000005530784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001446498,"about_ca_system_score_gemma":0.00004876392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004295166,"about_ca_topic_score_gemma":0.0001073279,"domain_scores_codex":[0.9994283,0.00003371228,0.0001708612,0.0001563504,0.0001510377,0.00005968346],"domain_scores_gemma":[0.9994005,0.00002965993,0.00004830456,0.000303159,0.0001738109,0.0000445396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000439865,0.0001571864,0.001230922,0.000008027911,0.00002301346,0.000006184208,0.01112752,0.0003283397,0.6568647,0.2727205,0.01619662,0.04133262],"study_design_scores_gemma":[0.0002210484,0.00002710697,0.0001653032,0.00000769197,0.00000378008,0.000002130207,0.00004434607,0.2488824,0.7009015,0.04938617,0.0002700682,0.00008844946],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009221827,0.000358946,0.9882604,0.000946993,0.00008982355,0.00008296998,0.000005878711,0.0002482792,0.0007848656],"genre_scores_gemma":[0.4860287,8.105708e-7,0.5137691,0.0000663752,0.00002617661,0.000006362955,0.0000156676,0.000001584678,0.00008513669],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4768069,"threshold_uncertainty_score":0.1607791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1004481952163301,"score_gpt":0.3160813897396517,"score_spread":0.2156331945233216,"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."}}