{"id":"W3157027354","doi":"10.25073/2588-1086/vnucsce.231","title":"Adaptation in Statistical Machine Translation for Low-resource Domains in English-Vietnamese Language","year":2020,"lang":"en","type":"article","venue":"VNU Journal of Science Computer Science and Communication Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine translation; Vietnamese; Artificial intelligence; Natural language processing; Computer science; Evaluation of machine translation; Phrase; Domain adaptation; Domain (mathematical analysis); Example-based machine translation; Machine translation software usability; Translation (biology); Baseline (sea); Classifier (UML); Linguistics; Mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002653978,0.0001003295,0.0001661337,0.0006228337,0.0001407325,0.0003212516,0.001943821,0.00002918418,4.270635e-7],"category_scores_gemma":[0.0005528044,0.0000907032,0.0000206003,0.002306024,0.0003433606,0.002419735,0.0002511051,0.0002737008,1.578381e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001253532,"about_ca_system_score_gemma":0.0002821553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008652472,"about_ca_topic_score_gemma":0.000005841622,"domain_scores_codex":[0.9985257,0.00003512541,0.000399001,0.0002466367,0.0005458107,0.0002477729],"domain_scores_gemma":[0.9989003,0.0002022122,0.000157344,0.0002571244,0.0003382019,0.0001448277],"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":[0.00003839134,0.0001020077,0.0002792894,0.0001102657,0.000003687013,0.00002169225,0.08570358,0.05474656,0.04739178,0.02778095,0.0000246402,0.7837971],"study_design_scores_gemma":[0.0003752036,0.0001037056,0.0005123666,0.0001172149,0.00000139742,0.00001444628,0.0002206402,0.9948115,0.003107765,0.0005408106,0.00008776825,0.0001071217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0359651,0.00183708,0.960532,0.00139358,0.00006550109,0.0001426375,0.00000114301,0.00005296485,0.000009987064],"genre_scores_gemma":[0.5469753,0.00002501095,0.4528528,0.0001225308,0.00001867784,0.000002586833,4.349335e-7,0.000002520109,1.252995e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.940065,"threshold_uncertainty_score":0.3698769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01327179269771563,"score_gpt":0.2582265781423414,"score_spread":0.2449547854446258,"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."}}