{"id":"W2117339222","doi":"","title":"Transductive learning for statistical machine translation","year":2007,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; National Research Council Canada","funders":"","keywords":"Machine translation; Computer science; NIST; Artificial intelligence; Natural language processing; Translation (biology); Strengths and weaknesses; Training set; Evaluation of machine translation; Machine translation software usability; Set (abstract data type); Quality (philosophy); Example-based machine translation; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.003083661,0.00120657,0.001269926,0.001590856,0.0005815809,0.002055847,0.001496874,0.001397082,0.003527578],"category_scores_gemma":[0.01105311,0.0005153838,0.0009746036,0.002522498,0.001897406,0.002789018,0.001819243,0.003332482,0.002483329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001457534,"about_ca_system_score_gemma":0.0007365689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009334374,"about_ca_topic_score_gemma":0.0008487122,"domain_scores_codex":[0.9972647,0.001590261,0.0001408282,0.0004152795,0.000521943,0.00006697878],"domain_scores_gemma":[0.9932013,0.00518146,0.0003065688,0.0008263674,0.0004235623,0.00006079521],"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":[0.0001423029,0.0002000129,0.0007757171,0.0009002562,0.0002762399,0.0002468281,0.0003268379,0.2577559,0.004537883,0.281973,0.01407773,0.4387873],"study_design_scores_gemma":[0.00001378622,0.00004482319,0.0001976972,0.00004066571,0.00001795184,0.00005396134,0.00002304864,0.6443999,0.001270181,0.3475408,0.006371995,0.00002508679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001646005,0.002073002,0.9926696,0.0005056466,0.0001041468,0.00006091642,0.0001335688,0.0007094001,0.002097595],"genre_scores_gemma":[0.287248,0.006303316,0.6939541,0.0008654317,0.001247811,0.001088615,0.001736206,0.0005497981,0.007006825],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003527578,"threshold_uncertainty_score":0.01630813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01672580944619226,"score_gpt":0.302467211369486,"score_spread":0.2857414019232937,"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."}}