تصف هذه الورقة مشاركة جامعة ماستريخت في مسار الترجمة متعددة اللغات في IWSLT 2021.المهمة في هذه المسار هي بناء أنظمة ترجمة خطاب متعددة اللغات في اتجاهات تحت إشراف ومطلة الصفر.نظامنا الأساسي هو نموذج نهاية إلى نهاية يؤدي إلى نسخ الكلام والترجمة.نلاحظ أن التدريب المشترك للمهامتين مكملتين خاصة عندما تكون بيانات ترجمة الكلام نادرة.على المصدر والجانب المستهدف، نستخدم تكبير البيانات والملصقات الزائفة على التوالي لتحسين أداء أنظمتنا.نقدم أيضا تقنية كفرية تعمل باستمرار على تحسين جودة النسخ والترجمات.تظهر التجارب أن النظام المنتهي تنافسية مع نظيره المتتالي وخاصة في ظروف الطلقة الصفرية.
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 is an end-to-end model that performs both speech transcription and translation. We observe that the joint training for the two tasks is complementary especially when the speech translation data is scarce. On the source and target side, we use data augmentation and pseudo-labels respectively to improve the performance of our systems. We also introduce an ensembling technique that consistently improves the quality of transcriptions and translations. The experiments show that the end-to-end system is competitive with its cascaded counterpart especially in zero-shot conditions.
References used
https://aclanthology.org/
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
In this paper, we describe Zhejiang University's submission to the IWSLT2021 Multilingual Speech Translation Task. This task focuses on speech translation (ST) research across many non-English source languages. Participants can decide whether to work
This paper describes KIT'submission to the IWSLT 2021 Offline Speech Translation Task. We describe a system in both cascaded condition and end-to-end condition. In the cascaded condition, we investigated different end-to-end architectures for the spe
This paper describes the ESPnet-ST group's IWSLT 2021 submission in the offline speech translation track. This year we made various efforts on training data, architecture, and audio segmentation. On the data side, we investigated sequence-level knowl
This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah's Ark Lab. We use a unified transformer architecture for our MultiST model, so that the data from different modalities (i.e.,