تقدم هذه الورقة التقديمات بجامعة ADAM MICKIECZ (AMU) لمهمة الترجمة الإخبارية WMT 2021.التركيز التقديمات على اتجاهات ترجمة English↔hausa، وهي سيناريو ترجمة موارد منخفضة بين اللغات البعيدة.ينطوي نهجنا على تنظيف بيانات شامل، ونقل التعلم باستخدام زوج لغة الموارد عالية الموارد، والتدريب التكراري، واستخدام بيانات أحادية المونولينغ عبر الترجمة الخلفي.نقوم بتجربة نهج NMT و PB-SMT على حد سواء، باستخدام بنية المحولات الأساسية لجميع نماذج NMT أثناء الاستفادة من أنظمة PB-SMT كحلول أساسية مماثلة.
This paper presents the Adam Mickiewicz University's (AMU) submissions to the WMT 2021 News Translation Task. The submissions focus on the English↔Hausa translation directions, which is a low-resource translation scenario between distant languages. Our approach involves thorough data cleaning, transfer learning using a high-resource language pair, iterative training, and utilization of monolingual data via back-translation. We experiment with NMT and PB-SMT approaches alike, using the base Transformer architecture for all of the NMT models while utilizing PB-SMT systems as comparable baseline solutions.
References used
https://aclanthology.org/
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
The paper describes the 3 NMT models submitted by the eTranslation team to the WMT 2021 news translation shared task. We developed systems in language pairs that are actively used in the European Commission's eTranslation service. In the WMT news tas
Neural Machine Translation (NMT) is a predominant machine translation technology nowadays because of its end-to-end trainable flexibility. However, NMT still struggles to translate properly in low-resource settings specifically on distant language pa
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
The machine translation efficiency task challenges participants to make their systems faster and smaller with minimal impact on translation quality. How much quality to sacrifice for efficiency depends upon the application, so participants were encou