{"id":"W4380995862","doi":"10.3390/app13127126","title":"An Optimized Approach to Translate Technical Patents from English to Japanese Using Machine Translation Models","year":2023,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Machine translation; Artificial intelligence; Natural language processing; Preprocessor; Evaluation of machine translation; Transformer; Translation (biology); Machine learning; Hyperparameter; BLEU; Example-based machine translation; Machine translation software usability; Engineering","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":[0.001000441,0.000189952,0.0002433974,0.0002982006,0.0003141273,0.0003393211,0.001768836,0.00008681881,0.000003891479],"category_scores_gemma":[0.00001130189,0.0001681587,0.00005138502,0.001984108,0.00006342943,0.0007337966,0.0001394181,0.0001278223,0.00002187809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002883496,"about_ca_system_score_gemma":0.00005640231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003286838,"about_ca_topic_score_gemma":0.00002212407,"domain_scores_codex":[0.9973969,0.00005490707,0.0003313416,0.001030526,0.0006992098,0.0004870967],"domain_scores_gemma":[0.9990034,0.00007383332,0.00004491772,0.0005642914,0.00004330085,0.0002702838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001345386,0.00004388484,0.00001385943,0.000003021192,0.000003526796,0.000001162313,0.01169212,0.9382294,0.02896778,0.003275088,0.000006463616,0.01775024],"study_design_scores_gemma":[0.0002968583,0.00003253906,0.00005942971,0.0000083135,0.000005706283,9.088927e-7,0.000284137,0.993877,0.0009107979,0.004267117,0.00002159226,0.000235636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2616619,0.00001613662,0.7344814,0.0002009995,0.0001590927,0.0004446835,0.000007458787,0.0004958338,0.002532487],"genre_scores_gemma":[0.5752469,0.000001096294,0.4244818,0.0001683761,0.00004668648,0.0000382879,0.000005780536,0.000007184331,0.0000039284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3135849,"threshold_uncertainty_score":0.6857314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1024625656874686,"score_gpt":0.303765753619348,"score_spread":0.2013031879318794,"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."}}