{"id":"W2105410942","doi":"10.3115/1620754.1620815","title":"Active learning for statistical phrase-based machine translation","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine translation; Artificial intelligence; Natural language processing; Phrase; Evaluation of machine translation; Example-based machine translation; Machine translation software usability; Sentence; Translation (biology); Selection (genetic algorithm); Active learning (machine learning); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004810693,0.0009530173,0.001361185,0.001235727,0.0007126657,0.001718728,0.002464624,0.001822537,0.003366398],"category_scores_gemma":[0.01409197,0.0008066691,0.0009195384,0.001856395,0.001551773,0.003084383,0.001798172,0.002888458,0.001441557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008438186,"about_ca_system_score_gemma":0.0008350175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001222873,"about_ca_topic_score_gemma":0.001317595,"domain_scores_codex":[0.9971397,0.001780347,0.0001568724,0.0003372503,0.0005035309,0.00008230156],"domain_scores_gemma":[0.9878522,0.009704027,0.0004701331,0.001002726,0.0008536833,0.0001172865],"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":[0.0003556407,0.0002151344,0.0005553273,0.0003629171,0.0001986532,0.0001630775,0.0001880389,0.424286,0.008145503,0.0655023,0.005160088,0.4948673],"study_design_scores_gemma":[0.00001838631,0.00003621641,0.00005410957,0.000008255513,0.000008107234,0.00002207312,0.00000670034,0.9678087,0.001712013,0.02909767,0.001218113,0.000009670515],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001713527,0.0003463783,0.9966283,0.000132992,0.00003900441,0.00002651416,0.00003494302,0.0005869557,0.000491421],"genre_scores_gemma":[0.2903874,0.001184806,0.7020301,0.0003238556,0.0004527654,0.0007194489,0.000676265,0.0003554003,0.003869876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004810693,"threshold_uncertainty_score":0.02544165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01667701950831549,"score_gpt":0.3063805958636106,"score_spread":0.2897035763552951,"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."}}