تصف هذه الورقة تقديم Papago إلى مهمة تقدير الجودة WMT 2021 1: التقييم المباشر على مستوى الجملة.يستكشف نظام تقدير الجودة متعدد اللغات لدينا مزيج من نماذج اللغة المحددة مسبقا وبنية التعلم متعددة المهام.نقترح خط أنابيب تدريب تكراري يعتمد على ما يحقظ بكميات كبيرة من البيانات الاصطناعية داخل المجال وتصفية البيانات الذهبية (المسمى).ثم قمنا بضغط نظامنا عبر تقطير المعرفة من أجل تقليل المعلمات بعد الحفاظ على أداء قوي.تنفذ أنظمتنا متعددة اللغات متعددة اللغات بشكل تنافسي في تعدد اللغات وجميع إعدادات زوج اللغة الفردية 11 بما في ذلك صفر النار.
This paper describes Papago submission to the WMT 2021 Quality Estimation Task 1: Sentence-level Direct Assessment. Our multilingual Quality Estimation system explores the combination of Pretrained Language Models and Multi-task Learning architectures. We propose an iterative training pipeline based on pretraining with large amounts of in-domain synthetic data and finetuning with gold (labeled) data. We then compress our system via knowledge distillation in order to reduce parameters yet maintain strong performance. Our submitted multilingual systems perform competitively in multilingual and all 11 individual language pair settings including zero-shot.
References used
https://aclanthology.org/
This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared task, focusing on the target-side word-level quality estimation. The tech
This paper presents Imperial College London's submissions to the WMT21 Quality Estimation (QE) Shared Task 3: Critical Error Detection. Our approach builds on cross-lingual pre-trained representations in a sequence classification model. We further im
We present the joint contribution of IST and Unbabel to the WMT 2021 Shared Task on Quality Estimation. Our team participated on two tasks: Direct Assessment and Post-Editing Effort, encompassing a total of 35 submissions. For all submissions, our ef
In this paper, we describe our submission to the WMT 2021 Metrics Shared Task. We use the automatically-generated questions and answers to evaluate the quality of Machine Translation (MT) systems. Our submission builds upon the recently proposed MTEQ
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