{"id":"W4389519857","doi":"10.18653/v1/2023.findings-emnlp.494","title":"Towards Formality-Aware Neural Machine Translation by Leveraging Context Information","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Samsung; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea; National Research Foundation","keywords":"Formality; Computer science; Machine translation; Classifier (UML); Artificial intelligence; Natural language processing; Machine learning; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.001157744,0.001011841,0.0007303178,0.0008534055,0.0005113787,0.00103046,0.00071864,0.0009580737,0.001553605],"category_scores_gemma":[0.004667663,0.0003583753,0.0006836271,0.0008396176,0.0007900323,0.002488578,0.001585665,0.001871821,0.000872009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006990673,"about_ca_system_score_gemma":0.001009864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002135127,"about_ca_topic_score_gemma":0.004551842,"domain_scores_codex":[0.9991055,0.0004060287,0.00006372249,0.0002283185,0.000139757,0.00005669439],"domain_scores_gemma":[0.9985449,0.0007362316,0.0001767968,0.0002619149,0.0002358166,0.00004437803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003826466,0.000177713,0.001747669,0.0003713227,0.0001250595,0.0002735471,0.0003986134,0.2044521,0.05608544,0.03100194,0.004811135,0.7001727],"study_design_scores_gemma":[0.00002105721,0.00005186852,0.0002475264,0.00002348259,0.00002826742,0.00008021558,0.00003796462,0.955693,0.007876166,0.03371131,0.002211847,0.00001717088],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02983311,0.0006699962,0.9648191,0.0003455924,0.00008598364,0.0000438819,0.0001065892,0.002285166,0.001810499],"genre_scores_gemma":[0.5509967,0.0005797324,0.4439078,0.0004351293,0.000154518,0.0001397757,0.0008626619,0.0004087482,0.002514955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002135127,"threshold_uncertainty_score":0.006122828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02126738435969645,"score_gpt":0.2732708674856432,"score_spread":0.2520034831259467,"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."}}