نقدم تطوير نظام الترجمة الآلي متعدد اللغات لمهمة الترجمة متعددة اللغات متعددة اللغات المهمة متعددة اللغات في WMT 2021. بدء تشغيل نظام الأساس المحتمل، حققنا في العديد من التقنيات لتحسين جودة الترجمة على المجموعة الفرعية المستهدفة من اللغات.تمكنا من تحسين جودة الترجمة بشكل كبير من خلال تكييف النظام باتجاه المجموعة الفرعية المستهدفة من اللغات وتوليد بيانات اصطناعية باستخدام النموذج الأولي.التقنيات المطبقة بنجاح في الترجمة متعددة اللغز المزدوجة (E.G. التشابه العادي) كان لها تأثير بسيط فقط على أداء الترجمة النهائي.
We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021. Starting form the provided baseline system, we investigated several techniques to improve the translation quality on the target subset of languages. We were able to significantly improve the translation quality by adapting the system towards the target subset of languages and by generating synthetic data using the initial model. Techniques successfully applied in zero-shot multilingual machine translation (e.g. similarity regularizer) only had a minor effect on the final translation performance.
References used
https://aclanthology.org/
This paper describes Maastricht University's participation in the IWSLT 2021 multilingual speech translation track. The task in this track is to build multilingual speech translation systems in supervised and zero-shot directions. Our primary system
We present the results of the first task on Large-Scale Multilingual Machine Translation. The task consists on the many-to-many evaluation of a single model across a variety of source and target languages. This year, the task consisted on three diffe
This paper describes TenTrans large-scale multilingual machine translation system for WMT 2021. We participate in the Small Track 2 in five South East Asian languages, thirty directions: Javanese, Indonesian, Malay, Tagalog, Tamil, English. We mainly
This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). In this work, we aim to build a single multilingual translation system with a hypothesis t
In this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT'21 Large Scale Multilingual Translation Task - Small Track 2. We submit a standard Seq2Seq Transformer model to the shared task without