{"id":"W2339504674","doi":"","title":"Learning Machine Translation from In-domain and Out-of-domain Data","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine translation; Computer science; Phrase; Natural language processing; Domain (mathematical analysis); Artificial intelligence; Translation (biology); Training set; Test data; Evaluation of machine translation; Language model; Machine learning; Example-based machine translation; Machine translation software usability; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005024294,0.00006835042,0.0001046591,0.00006379581,0.00003541264,0.00003111214,0.0005261682,0.0000444593,0.00001432076],"category_scores_gemma":[0.00004168015,0.00006071736,0.000009099171,0.0001244831,0.00002702418,0.0007316134,0.0002371224,0.0001676144,0.000002273264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001016466,"about_ca_system_score_gemma":0.000009291663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004296522,"about_ca_topic_score_gemma":0.00003702279,"domain_scores_codex":[0.9993164,0.00008034482,0.0001344865,0.0001885454,0.0001344348,0.0001457941],"domain_scores_gemma":[0.9994519,0.00009316136,0.00005874896,0.0003483499,0.00001003238,0.0000377774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001641075,0.00006324922,0.02469756,0.00003323595,0.000009922979,0.000007855114,0.01201529,9.859112e-7,0.1622255,0.01804508,0.0001261163,0.7827588],"study_design_scores_gemma":[0.001782886,0.0001735992,0.0128888,0.0003364627,0.00002280825,0.00001979518,0.0003146502,0.1079564,0.04891812,0.8102462,0.01644888,0.0008913919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08893537,0.00538998,0.9027461,0.0007602985,0.0001229014,0.0001065067,0.00001153174,0.0001770356,0.001750283],"genre_scores_gemma":[0.5221193,0.000007963484,0.4778083,0.00002041959,0.00002135118,0.000001038395,0.00001351245,0.000003019563,0.000005117474],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7922012,"threshold_uncertainty_score":0.2475982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03243895225103998,"score_gpt":0.2932855740325661,"score_spread":0.2608466217815261,"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."}}