{"id":"W2132187905","doi":"10.1109/tasl.2010.2040793","title":"Integration of Statistical Models for Dictation of Document Translations in a Machine-Aided Human Translation Task","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Computer science; Dictation; Machine translation; Natural language processing; NIST; Language model; Artificial intelligence; Word error rate; Speech translation; Baseline (sea); Task (project management); Speech recognition; Vocabulary; Machine translation software usability; Translation (biology); Word (group theory); Evaluation of machine translation; Example-based machine translation; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003723278,0.0001488609,0.0002229457,0.0003593299,0.0001150917,0.00006185513,0.0001871706,0.0001121793,0.00000794986],"category_scores_gemma":[0.0000157087,0.0001358703,0.00005349513,0.0003640599,0.00007571976,0.0008169031,0.000001346398,0.0002806603,1.39029e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000206607,"about_ca_system_score_gemma":0.00006114285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001481251,"about_ca_topic_score_gemma":0.0009410568,"domain_scores_codex":[0.9988544,0.00004634104,0.0004383168,0.0002818453,0.0002199736,0.0001591128],"domain_scores_gemma":[0.9993507,0.0001435811,0.0001675745,0.000174725,0.0001157418,0.00004767954],"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":[0.00003577389,0.0000992956,0.000003516317,0.0001487376,0.000005962073,0.00000139958,0.004509862,0.0002687484,0.389766,0.002109982,0.000001038502,0.6030497],"study_design_scores_gemma":[0.0009450576,0.0001760301,0.00004528329,0.0002043007,0.00003625095,0.00001182458,0.0001974418,0.3958244,0.5735389,0.02882205,0.000002830911,0.0001955659],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03067753,0.0006149473,0.9678808,0.000156044,0.00005075138,0.0004182556,0.00004749781,0.0001044261,0.00004972635],"genre_scores_gemma":[0.5899518,0.000006442265,0.4099583,0.00001304129,0.00000647802,0.00003578176,0.00001188632,0.000008113215,0.000008217408],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6028541,"threshold_uncertainty_score":0.554063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01567801898789683,"score_gpt":0.3061881551732855,"score_spread":0.2905101361853886,"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."}}