{"id":"W2157616430","doi":"10.1017/s1351324908004737","title":"Multilingual pronunciation by analogy","year":2008,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Pronunciation; Transcription (linguistics); Natural language processing; Orthography; Spelling; Analogy; Artificial intelligence; Variation (astronomy); Phonetic transcription; Linguistics; Speech recognition","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":[0.0001177472,0.0001763281,0.0001554626,0.0001396438,0.0000876761,0.00004844585,0.0006054852,0.0001035272,0.000006599016],"category_scores_gemma":[0.0002495014,0.0001577134,0.00005429528,0.0003862715,0.00001718809,0.0005220236,0.0001299876,0.0003858211,0.0000134469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108176,"about_ca_system_score_gemma":0.00003543563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004781986,"about_ca_topic_score_gemma":0.000003284512,"domain_scores_codex":[0.9988987,0.00001700918,0.0001767665,0.0003130604,0.0002748622,0.0003196423],"domain_scores_gemma":[0.9994406,0.00005734099,0.00005915239,0.0003072573,0.00006834711,0.00006736026],"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":[0.00001346929,0.00009012698,0.0004206257,0.0001098765,0.00005691723,0.0008007649,0.008427103,0.0003954436,0.7306762,0.005814369,0.005573642,0.2476215],"study_design_scores_gemma":[0.0005758985,0.0000752187,0.0005774476,0.00006317936,0.000008472651,0.0005398288,0.00004355914,0.2401359,0.7539868,0.000142575,0.002985261,0.0008659188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3921237,0.05529143,0.5461189,0.0003483098,0.0009748695,0.0003567229,0.000008486305,0.004578122,0.0001994379],"genre_scores_gemma":[0.7724401,0.00001004908,0.2270218,0.0001156537,0.00009729596,0.000009342285,0.00001574393,0.00001434007,0.0002756816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3803164,"threshold_uncertainty_score":0.6431366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004698680563171272,"score_gpt":0.2267604826131823,"score_spread":0.222061802050011,"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."}}