{"id":"W3208011254","doi":"","title":"Bilingual Methods for Adaptive Training Data Selection for Machine Translation","year":2016,"lang":"en","type":"article","venue":"Conference of the Association for Machine Translation in the Americas","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Machine translation; Computer science; Artificial intelligence; Selection (genetic algorithm); Convolutional neural network; Translation (biology); Sentence; Natural language processing; Machine learning; Task (project management); Adaptation (eye); Artificial neural network; BLEU; Domain adaptation; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002822145,0.0009930979,0.0008465656,0.001192436,0.0007422733,0.0005675161,0.001425498,0.000685122,0.003764963],"category_scores_gemma":[0.005065753,0.000498721,0.0007340288,0.00137902,0.0005079124,0.001598856,0.00176527,0.001100945,0.001935304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005802523,"about_ca_system_score_gemma":0.001153684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001877684,"about_ca_topic_score_gemma":0.004704964,"domain_scores_codex":[0.9978786,0.000964703,0.0001751418,0.0004955498,0.0003910479,0.00009511239],"domain_scores_gemma":[0.9977707,0.0009444737,0.0001613732,0.0005348318,0.0005115939,0.0000770308],"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":[0.0006677131,0.0003731507,0.0031655,0.0003269176,0.0002075115,0.0001992377,0.0003436619,0.09207065,0.04484657,0.01446255,0.007482287,0.8358543],"study_design_scores_gemma":[0.0001027643,0.0001559872,0.001088145,0.00002486602,0.00004665242,0.0001507488,0.00008000703,0.9495845,0.02514705,0.01313296,0.01045313,0.00003317232],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01176892,0.0002639098,0.9850143,0.00008550853,0.00005313985,0.00007884419,0.0001335867,0.001477433,0.001124442],"genre_scores_gemma":[0.228935,0.0002989608,0.7624675,0.0003581683,0.0001534636,0.0007051707,0.002405896,0.0006713307,0.004004493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003764963,"threshold_uncertainty_score":0.01492512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1617180959017715,"score_gpt":0.41267138165388,"score_spread":0.2509532857521085,"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."}}