{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001196713,0.00007275763,0.00007695422,0.0000559946,0.00007940203,0.0000732159,0.0002226398,0.00003894378,0.00001625301],"category_scores_gemma":[0.00007268369,0.00005904525,0.0000259898,0.0001226223,0.00001099829,0.0002494543,0.000007559625,0.0001130145,0.000002628791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002130975,"about_ca_system_score_gemma":0.00003062843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007859042,"about_ca_topic_score_gemma":0.000003169144,"domain_scores_codex":[0.9994378,0.0000267349,0.00009160748,0.0001904147,0.0001165859,0.0001368355],"domain_scores_gemma":[0.9996375,0.0001401479,0.00003275017,0.0001061541,0.00004708723,0.0000363032],"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":[0.00002472851,0.00002468904,0.000006466919,0.00000589518,0.000001546346,0.000002268214,0.00008611716,0.00004080909,0.003484157,0.06546438,0.0001358913,0.9307231],"study_design_scores_gemma":[0.0004071937,0.0002948703,0.0001240889,0.00001198783,0.000004749574,0.000002215884,0.0000034439,0.8551302,0.06612311,0.07674177,0.001008372,0.0001479947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009078106,0.0001974108,0.9964256,0.001886783,0.00001950442,0.0001518104,0.000002739354,0.0006759886,0.0005493278],"genre_scores_gemma":[0.4610032,3.27159e-7,0.5385771,0.0003528829,0.00001019736,0.000004567596,0.00001151282,0.00000217037,0.00003811205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9305751,"threshold_uncertainty_score":0.2407795,"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."}}