تصف هذه الورقة أنظمة Fujitsu Dmath المستخدمة لترجمة WMT 2021، ومهام الترجمة الطبية الحيوية.ركزنا على أزواج منخفضة الموارد، باستخدام نظام بسيط.أجرينا تجارب على اللغة الإنجليزية هوسا، Xhosa-Zulu والإنجليزية-الباسك، وقدمت نتائج Xhosa → Zulu في مهمة ترجمة الأخبار، والإنجليزية → الباسك في مهمة الترجمة الطبية الحيوية، ومصادر الترجمة التابعة للمصطلح والمصطلحات.يجمع نظامنا بين تسرب BPE، ميزات الكلمات الفرعية الفرعية والترجمة الخلفي مع نموذج محول (قاعدة)، وتحقيق نتائج جيدة على مجموعات التقييم.
This paper describes the Fujitsu DMATH systems used for WMT 2021 News Translation and Biomedical Translation tasks. We focused on low-resource pairs, using a simple system. We conducted experiments on English-Hausa, Xhosa-Zulu and English-Basque, and submitted the results for Xhosa→Zulu in the News Translation Task, and English→Basque in the Biomedical Translation Task, abstract and terminology translation subtasks. Our system combines BPE dropout, sub-subword features and back-translation with a Transformer (base) model, achieving good results on the evaluation sets.
References used
https://aclanthology.org/
This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC). Technical details are introduced
In this paper we present the FJWU's system submitted to the biomedical shared task at WMT21. We prepared state-of-the-art multilingual neural machine translation systems for three languages (i.e. German, Spanish and French) with English as target lan
This paper presents the University of Edinburgh's constrained submissions of English-German and English-Hausa systems to the WMT 2021 shared task on news translation. We build En-De systems in three stages: corpus filtering, back-translation, and fin
This paper describes the Tencent AI Lab submission of the WMT2021 shared task on biomedical translation in eight language directions: English-German, English-French, English-Spanish and English-Russian. We utilized different Transformer architectures
We submitted two uni-directional models, one for English→Icelandic direction and other for Icelandic→English direction. Our news translation system is based on the transformer-big architecture, it makes use of corpora filtering, back-translation and