تصف هذه الورقة مهمة Charles University الفرعية للمصطلحات المهمة المشتركة للترجمة في WMT21.الهدف من هذه المهمة هو تصميم نظام يترجم مع شروط معينة بناء على قاعدة بيانات المصطلحات المقدمة، مع الحفاظ على جودة الترجمة الشاملة عالية.تنافسنا في زوج اللغة الإنجليزية الفرنسية.يعتمد نهجنا على توفير الترجمات المرغوبة إلى جانب جملة الإدخال وتدريب النموذج لاستخدام هذه المصطلحات المقدمة.نحن Lemmatize المصطلحات على حد سواء أثناء التدريب والاستدلال، للسماح للنموذج لمعرفة كيفية إنتاج الأشكال السطحية الصحيحة للكلمات، عندما تختلف عن النماذج المتوفرة في قاعدة بيانات المصطلحات.
This paper describes Charles University sub-mission for Terminology translation shared task at WMT21. The objective of this task is to design a system which translates certain terms based on a provided terminology database, while preserving high overall translation quality. We competed in English-French language pair. Our approach is based on providing the desired translations alongside the input sentence and training the model to use these provided terms. We lemmatize the terms both during the training and inference, to allow the model to learn how to produce correct surface forms of the words, when they differ from the forms provided in the terminology database.
References used
https://aclanthology.org/
This paper describes TenTrans' submission to WMT21 Multilingual Low-Resource Translation shared task for the Romance language pairs. This task focuses on improving translation quality from Catalan to Occitan, Romanian and Italian, with the assistance
This paper describes Charles University sub-mission for Terminology translation Shared Task at WMT21. The objective of this task is to design a system which translates certain terms based on a provided terminology database, while preserving high over
This paper describes the participation of the BSC team in the WMT2021's Multilingual Low-Resource Translation for Indo-European Languages Shared Task. The system aims to solve the Subtask 2: Wikipedia cultural heritage articles, which involves transl
In this work, we investigate methods for the challenging task of translating between low- resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between several Indo-
This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. We participated in all three evaluation tracks including Large Track and two Small Tracks where the former one is