{"id":"W2151594415","doi":"","title":"Mixing Multiple Translation Models in Statistical Machine Translation","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Simon Fraser University","funders":"","keywords":"Machine translation; Computer science; Decoding methods; Translation (biology); Domain adaptation; Artificial intelligence; Domain (mathematical analysis); Transfer-based machine translation; Example-based machine translation; Natural language processing; Statistical model; Adaptation (eye); Machine learning; Algorithm; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003186858,0.00008451039,0.00009368675,0.0001016474,0.00003896141,0.00004365321,0.0002317453,0.00006073841,0.00001789864],"category_scores_gemma":[0.00002484347,0.00007806521,0.00001938306,0.0002103599,0.00001584023,0.00114536,0.00002056131,0.0001536497,0.000004873249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003135868,"about_ca_system_score_gemma":0.00001426134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003186693,"about_ca_topic_score_gemma":0.0000285396,"domain_scores_codex":[0.9991899,0.00005935948,0.0001687367,0.0001609406,0.0001865325,0.0002344955],"domain_scores_gemma":[0.9995986,0.0001408265,0.00003132648,0.0001556818,0.00001799389,0.00005555732],"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":[0.00001295274,0.00006873765,0.001007259,0.00002550544,0.00000237733,0.000003699928,0.002842926,0.00009630283,0.02759477,0.08303387,0.0000408083,0.8852708],"study_design_scores_gemma":[0.0002300736,0.0000125123,0.000290987,0.00001854246,0.000002187864,0.00000490612,0.000003855693,0.8467197,0.006768591,0.1457298,0.000106315,0.0001125392],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001812019,0.001524446,0.9942595,0.0004145128,0.00006405276,0.0001274852,0.000004801177,0.000246546,0.001546621],"genre_scores_gemma":[0.5140898,0.000003206972,0.4858327,0.00003780927,0.00001648402,0.000006330439,0.000006231227,0.000003995707,0.000003419263],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8851582,"threshold_uncertainty_score":0.3183407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0363817459436489,"score_gpt":0.2902666161091048,"score_spread":0.2538848701654559,"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."}}