{"id":"W117861810","doi":"","title":"Using monolingual source-language data to improve MT performance.","year":2006,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency","keywords":"Computer science; Natural language processing; Machine translation; Artificial intelligence; Phrase; Translation (biology); Focus (optics); Task (project management); Domain (mathematical analysis); Example-based machine translation; Training set; Source text","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004847022,0.001596575,0.001181282,0.002817627,0.0008437848,0.001451285,0.001303784,0.00115518,0.009004463],"category_scores_gemma":[0.02106567,0.0005001377,0.0005177194,0.003096931,0.0003963843,0.003268992,0.00200878,0.001294346,0.01422693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004958053,"about_ca_system_score_gemma":0.0006937617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00183045,"about_ca_topic_score_gemma":0.005783081,"domain_scores_codex":[0.9958846,0.002661508,0.0002091581,0.0005473028,0.0006071465,0.0000903178],"domain_scores_gemma":[0.9862096,0.006490724,0.0006206468,0.003238738,0.003240045,0.0002002751],"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":[0.001130823,0.0008323806,0.009930779,0.002199175,0.000571753,0.0006097491,0.0005993291,0.01771034,0.1397744,0.002462382,0.03171419,0.7924647],"study_design_scores_gemma":[0.0004975445,0.002124095,0.04188211,0.0008011783,0.0008917675,0.003436518,0.0008793753,0.3861772,0.3628951,0.01683948,0.1831832,0.0003923351],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2071456,0.008247134,0.7176546,0.00198727,0.0008699149,0.0009247744,0.008965819,0.025785,0.02841974],"genre_scores_gemma":[0.4134515,0.002354586,0.5341724,0.0006752025,0.0003865345,0.0006114234,0.03166233,0.001753393,0.01493271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009004463,"threshold_uncertainty_score":0.03012294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03111970941160225,"score_gpt":0.3021307769701553,"score_spread":0.271011067558553,"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."}}