{"id":"W2118947254","doi":"","title":"Applying Many-to-Many Alignments and Hidden Markov Models to Letter-to-Phoneme Conversion","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Bigram; Hidden Markov model; Computer science; Chunking (psychology); Speech recognition; Artificial intelligence; Preprocessor; Word (group theory); Training set; Conjunction (astronomy); Natural language processing; Viterbi algorithm; Trigram","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":[0.0005433139,0.0001876956,0.0001678951,0.0003036018,0.0001296831,0.000220304,0.000893684,0.00008477399,0.00001583319],"category_scores_gemma":[0.00001788082,0.0001666849,0.00002844468,0.0004701309,0.0000149911,0.0005385133,0.001140583,0.0001288445,0.00009155578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009883246,"about_ca_system_score_gemma":0.00001331201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001496742,"about_ca_topic_score_gemma":0.000009407534,"domain_scores_codex":[0.9982992,0.00002139193,0.0002242511,0.0005821572,0.0004198501,0.0004531193],"domain_scores_gemma":[0.9990374,0.00005238787,0.00004385354,0.000470964,0.00006461723,0.0003307318],"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":[0.0000835699,0.00007894803,0.0003587148,0.00008983717,0.00002782109,0.0002123122,0.003787526,0.00002186764,0.1679042,0.02320329,0.08818282,0.716049],"study_design_scores_gemma":[0.001217794,0.0006188645,0.0007747057,0.0005190563,0.00002657396,0.0001033244,0.0003351323,0.06580026,0.8538453,0.03568674,0.03865198,0.002420275],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02152159,0.00009658305,0.9728091,0.002437085,0.0001569563,0.0007072369,0.000001149657,0.0005767114,0.001693548],"genre_scores_gemma":[0.3744174,0.000001524916,0.6088279,0.01588454,0.00005418439,0.0000321775,6.97569e-7,0.00001091377,0.0007706259],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7136288,"threshold_uncertainty_score":0.6797214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0158162935609305,"score_gpt":0.2610017271666965,"score_spread":0.2451854336057659,"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."}}