Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNetmarble AI Center's WMT21 Automatic Post-Editing Shared Task Submission
التلقائي التلقائي في NetMarble AI Center
72
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توضح هذه الورقة تقديم NetMarble إلى مهمة مشاركة WMT21 التلقائية بعد التحرير (القرد) لزوج اللغة الإنجليزية الألمانية. أولا، نقترح استراتيجية تدريب المناهج الدراسية في مراحل التدريب. تم اختيار نموذج الترجمة من WMT19 Face Facebook لإشراك الشبكات العصبية الكبيرة والقوية المدربة مسبقا. ثم، نقوم بتنفيذ نموذج الترجمة بمستويات مختلفة من البيانات في كل مراحل تدريبية. مع استمرار مراحل التدريب، نجعل النظام يتعلم حل مهام متعددة عن طريق إضافة معلومات إضافية في مراحل التدريب المختلفة تدريجيا. نعرض أيضا طريقة لاستخدام البيانات الإضافية في حجم كبير لمهام القرد. لمزيد من التحسين، نطبق استراتيجية التعلم متعددة المهام مع متوسط الوزن الديناميكي خلال مرحلة ضبط الدقيقة. لضبط Corpus القرد مع بيانات محدودة، نضيف بعض المهام الفرعية ذات الصلة لتعلم تمثيل موحد. أخيرا، للحصول على أداء أفضل، نستفيد الترجمات الخارجية كترجمة آلية ازدهار (MT) أثناء التدريب على ما بعد التدريب والضبط. كما تظهر النتائج التجريبية، يعمل نظام القرد لدينا بشكل كبير على تحسين ترجمات نتائج MT المقدمة بنسبة -2.848 و +3.74 على مجموعة بيانات التطوير من حيث TER و Bleu، على التوالي. كما يوضح فعاليته في مجموعة بيانات الاختبار بجودة أعلى من مجموعة بيانات التطوير.
This paper describes Netmarble's submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. First, we propose a Curriculum Training Strategy in training stages. Facebook Fair's WMT19 news translation model was chosen to engage the large and powerful pre-trained neural networks. Then, we post-train the translation model with different levels of data at each training stages. As the training stages go on, we make the system learn to solve multiple tasks by adding extra information at different training stages gradually. We also show a way to utilize the additional data in large volume for APE tasks. For further improvement, we apply Multi-Task Learning Strategy with the Dynamic Weight Average during the fine-tuning stage. To fine-tune the APE corpus with limited data, we add some related subtasks to learn a unified representation. Finally, for better performance, we leverage external translations as augmented machine translation (MT) during the post-training and fine-tuning. As experimental results show, our APE system significantly improves the translations of provided MT results by -2.848 and +3.74 on the development dataset in terms of TER and BLEU, respectively. It also demonstrates its effectiveness on the test dataset with higher quality than the development dataset.
References used
https://aclanthology.org/
rate research
Read More
Accurate translation requires document-level information, which is ignored by sentence-level machine translation. Recent work has demonstrated that document-level consistency can be improved with automatic post-editing (APE) using only target-languag
e (TL) information. We study an extended APE model that additionally integrates source context. A human evaluation of fluency and adequacy in English--Russian translation reveals that the model with access to source context significantly outperforms monolingual APE in terms of adequacy, an effect largely ignored by automatic evaluation metrics. Our results show that TL-only modelling increases fluency without improving adequacy, demonstrating the need for conditioning on source text for automatic post-editing. They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.
This paper describes the Tencent AI Lab submission of the WMT2021 shared task on biomedical translation in eight language directions: English-German, English-French, English-Spanish and English-Russian. We utilized different Transformer architectures
, pretraining and back-translation strategies to improve translation quality. Concretely, we explore mBART (Liu et al., 2020) to demonstrate the effectiveness of the pretraining strategy. Our submissions (Tencent AI Lab Machine Translation, TMT) in German/French/Spanish⇒English are ranked 1st respectively according to the official evaluation results in terms of BLEU scores.
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 architecture
s. 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.
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
niques we experimented with include Levenshtein Transformer training and data augmentation with a combination of forward, backward, round-trip translation, and pseudo post-editing of the MT output. We demonstrate the competitiveness of our system compared to the widely adopted OpenKiwi-XLM baseline. Our system is also the top-ranking system on the MT MCC metric for the English-German language pair.
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
prove the base classifier by (i) adding a weighted sampler to deal with unbalanced data and (ii) introducing feature engineering, where features related to toxicity, named-entities and sentiment, which are potentially indicative of critical errors, are extracted using existing tools and integrated to the model in different ways. We train models with one type of feature at a time and ensemble those models that improve over the base classifier on the development (dev) set. Our official submissions achieve very competitive results, ranking second for three out of four language pairs.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
