{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005517837,0.001330114,0.001232427,0.00184113,0.0007376827,0.001768395,0.00108554,0.001329322,0.001809382],"category_scores_gemma":[0.02614501,0.0005862165,0.0009419553,0.002468323,0.0009125376,0.003341201,0.001840375,0.002047887,0.002083627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009019863,"about_ca_system_score_gemma":0.00120961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003393136,"about_ca_topic_score_gemma":0.005114004,"domain_scores_codex":[0.9971514,0.001501882,0.0002345968,0.0005328969,0.0004512601,0.0001279805],"domain_scores_gemma":[0.9832449,0.01179818,0.0005961705,0.002360181,0.001825122,0.0001755259],"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":[0.0008834513,0.0004701143,0.01768382,0.0007375522,0.0004061065,0.0004076714,0.0005639262,0.3696831,0.01948347,0.004758707,0.005798806,0.5791233],"study_design_scores_gemma":[0.00004845671,0.0002286907,0.005956939,0.00004067798,0.00007364166,0.000195073,0.0001769143,0.96236,0.02019176,0.007205423,0.003482433,0.0000401322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5702111,0.002717834,0.4097617,0.001007569,0.0001854241,0.0002148287,0.002114672,0.006108149,0.007678753],"genre_scores_gemma":[0.808058,0.0007301604,0.1782324,0.0002072004,0.00008943873,0.0003021368,0.008375671,0.0006073343,0.003397636],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005517837,"threshold_uncertainty_score":0.02918148,"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."}}