Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTencent Translation System for the WMT21 News Translation Task
نظام الترجمة Tencent لمهمة ترجمة الأخبار WMT21
386
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة أنظمة Tencent Translation ذات المهمة المشتركة WMT21. نشارك في مهمة ترجمة الأخبار على ثلاث أزواج لغة: الصينية-الإنجليزية والإنجليزية والصينية والألمانية والإنجليزية. يتم بناء أنظمتنا على نماذج محولات مختلفة مع تقنيات جديدة تتكيف من عملنا البحثي الأخير. أولا، نجمع بين طرق تكبير البيانات المختلفة بما في ذلك الترجمة المرجودة والترجمة الأمامية والتدريب من اليمين إلى اليسار لتوسيع بيانات التدريب. نستخدم أيضا تحيز التغطية اللغوية وتجديد البيانات ونهج أخذ العينات المستندة إلى عدم اليقين لتحديد بيانات ذات صلة بالمحتوى وعالية الجودة من كوربورا متوازية ومونولجة كبيرة. نتوقع أن يتم ضبطه بشكل جيد في المجال، ونقترح أيضا نماذج واحدة المحبوثة نموذج واحد "" لنموذج خصائص نموذجية لأنواع الأخبار المختلفة عند مراحل الركود الدقيقة وفك التشفير. علاوة على ذلك، نستخدم خوارزمية الفرقة القائمة على الجشع وطريقة الفرقة المتناقلة لتعزيز أنظمتنا. بناء على نجاحنا في آخر WMT، فإننا أعملنا باستمرار تقنيات متقدمة مثل التدريب الدفاعي الكبير واختيار البيانات وتصفية البيانات. أخيرا، يحقق نظامنا الصيني والإنجليزي المقيد 33.4 درجة بلو حساسة للحالة، وهو الأعلى بين جميع التقديمات. يتم تصنيف نظام اللغة الإنجليزية الألمانية في المركز الثاني وفقا لذلك.
This paper describes Tencent Translation systems for the WMT21 shared task. We participate in the news translation task on three language pairs: Chinese-English, English-Chinese and German-English. Our systems are built on various Transformer models with novel techniques adapted from our recent research work. First, we combine different data augmentation methods including back-translation, forward-translation and right-to-left training to enlarge the training data. We also apply language coverage bias, data rejuvenation and uncertainty-based sampling approaches to select content-relevant and high-quality data from large parallel and monolingual corpora. Expect for in-domain fine-tuning, we also propose a fine-grained one model one domain'' approach to model characteristics of different news genres at fine-tuning and decoding stages. Besides, we use greed-based ensemble algorithm and transductive ensemble method to further boost our systems. Based on our success in the last WMT, we continuously employed advanced techniques such as large batch training, data selection and data filtering. Finally, our constrained Chinese-English system achieves 33.4 case-sensitive BLEU score, which is the highest among all submissions. The German-English system is ranked at second place accordingly.
References used
https://aclanthology.org/
rate research
Read More
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 DUT-NLP Lab's submission to the WMT-21 triangular machine translation shared task. The participants are not allowed to use other data and the translation direction of this task is Russian-to-Chinese. In this task, we use the Tran
sformer as our baseline model, and integrate several techniques to enhance the performance of the baseline, including data filtering, data selection, fine-tuning, and post-editing. Further, to make use of the English resources, such as Russian/English and Chinese/English parallel data, the relationship triangle is constructed by multilingual neural machine translation systems. As a result, our submission achieves a BLEU score of 21.9 in Russian-to-Chinese.
We submitted two uni-directional models, one for English→Icelandic direction and other for Icelandic→English direction. Our news translation system is based on the transformer-big architecture, it makes use of corpora filtering, back-translation and
forward translation applied to parallel and monolingual data alike
This paper describes the PROMT submissions for the WMT21 Terminology Translation Task. We participate in two directions: English to French and English to Russian. Our final submissions are MarianNMT-based neural systems. We present two technologies f
or terminology translation: a modification of the Dinu et al. (2019) soft-constrained approach and our own approach called PROMT Smart Neural Dictionary (SmartND). We achieve good results in both directions.
In this work, two Neural Machine Translation (NMT) systems have been developed and evaluated as part of the bidirectional Tamil-Telugu similar languages translation subtask in WMT21. The OpenNMT-py toolkit has been used to create quick prototypes of
the systems, following which models have been trained on the training datasets containing the parallel corpus and finally the models have been evaluated on the dev datasets provided as part of the task. Both the systems have been trained on a DGX station with 4 -V100 GPUs. The first NMT system in this work is a Transformer based 6 layer encoder-decoder model, trained for 100000 training steps, whose configuration is similar to the one provided by OpenNMT-py and this is used to create a model for bidirectional translation. The second NMT system contains two unidirectional translation models with the same configuration as the first system, with the addition of utilizing Byte Pair Encoding (BPE) for subword tokenization through the pre-trained MultiBPEmb model. Based on the dev dataset evaluation metrics for both the systems, the first system i.e. the vanilla Transformer model has been submitted as the Primary system. Since there were no improvements in the metrics during training of the second system with BPE, it has been submitted as a contrastive system.
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
