{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003503351,0.0001706907,0.0002843751,0.0001284141,0.0002140247,0.0000812033,0.001552464,0.0001070924,0.000002556421],"category_scores_gemma":[0.001570397,0.00009821468,0.0001538702,0.0005189178,0.00005273911,0.0007075788,0.00004228244,0.0001345366,2.270814e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001017001,"about_ca_system_score_gemma":0.0001853647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006939435,"about_ca_topic_score_gemma":0.0001793109,"domain_scores_codex":[0.998192,0.0004057424,0.0004869365,0.000400063,0.0002590802,0.0002561725],"domain_scores_gemma":[0.9940511,0.004346432,0.0007078503,0.0004948191,0.0003780721,0.00002170158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001327545,0.00004105356,0.0002597923,0.00002953913,0.00004080407,1.424271e-8,0.00394609,0.00004539909,0.01108631,0.02152627,0.00005672363,0.9628353],"study_design_scores_gemma":[0.001745183,0.0002977861,0.0002877817,0.00008798204,0.0001008745,0.000002543286,0.0001266592,0.8232998,0.01190373,0.1584632,0.003431238,0.0002533088],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001809687,0.0007201341,0.9881204,0.008814307,0.0001707034,0.001547797,0.0002634694,0.0001098018,0.00007236323],"genre_scores_gemma":[0.4877024,0.00001118644,0.5119215,0.00009372667,0.00003896374,0.0001281985,0.00004568531,0.00001096014,0.00004735222],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9625819,"threshold_uncertainty_score":0.4005078,"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."}}