Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userThe IICT-Yverdon System for the WMT 2021 Unsupervised MT and Very Low Resource Supervised MT Task
نظام IICT-Yverdon ل WMT 2021 MT غير الخاضعة للإشراف ومهمة MT منخفضة للغاية
487
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه الورقة، نقدم النظم المقدمة من فريقنا من معهد تكنولوجيا المعلومات والاتصالات (HIGH-VD / HES-SO) إلى مهمة MT غير الخاضعة للرقابة والموارد منخفضة للغاية.ندرس أولا التحسينات التي جلبت إلى نظام أساسي من خلال تقنيات مثل الترجمة الخلفي والتهيئة من نموذج الوالدين.نجد أن كلتا التقنيتين مفيدة وكافية للوصول إلى الأداء الذي يقارن مع أنظمة أكثر تطورا من مهمة 2020.بعد ذلك، نقدم تطبيق هذا النظام إلى مهمة 2021 للمزيد من الأغراض السربية العلوي تحت الإشراف (HSB) إلى الترجمة الألمانية، في كلا الاتجاهين.أخيرا، نقدم نظاما نظعا ل HSB-DE في كلا الاتجاهين، وللترجمة الألمانية غير الخاضعة للرقابة إلى أسفل ترجمة Sorbian (DSB)، والتي تستخدم التدريب المتعدد المهام مع مختلف جداول التدريب لتحسين الخط الأساسي.
In this paper, we present the systems submitted by our team from the Institute of ICT (HEIG-VD / HES-SO) to the Unsupervised MT and Very Low Resource Supervised MT task. We first study the improvements brought to a baseline system by techniques such as back-translation and initialization from a parent model. We find that both techniques are beneficial and suffice to reach performance that compares with more sophisticated systems from the 2020 task. We then present the application of this system to the 2021 task for low-resource supervised Upper Sorbian (HSB) to German translation, in both directions. Finally, we present a contrastive system for HSB-DE in both directions, and for unsupervised German to Lower Sorbian (DSB) translation, which uses multi-task training with various training schedules to improve over the baseline.
References used
https://aclanthology.org/
rate research
Read More
We present the findings of the WMT2021 Shared Tasks in Unsupervised MT and Very Low Resource Supervised MT. Within the task, the community studied very low resource translation between German and Upper Sorbian, unsupervised translation between German
and Lower Sorbian and low resource translation between Russian and Chuvash, all minority languages with active language communities working on preserving the languages, who are partners in the evaluation. Thanks to this, we were able to obtain most digital data available for these languages and offer them to the task participants. In total, six teams participated in the shared task. The paper discusses the background, presents the tasks and results, and discusses best practices for the future.
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task. We participate in the Russian-to-Chinese task under the constrained condition. We use Transformer architecture and obtain the best
performance via a variant with larger parameter sizes. We perform detailed data pre-processing and filtering on the provided large-scale bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, Data Denoising, Average Checkpoint, Ensemble, Fine-tuning, etc. Our system obtains 32.5 BLEU on the dev set and 27.7 BLEU on the test set, the highest score among all submissions.
This paper describes the NoahNMT system submitted to the WMT 2021 shared task of Very Low Resource Supervised Machine Translation. The system is a standard Transformer model equipped with our recent technique of dual transfer. It also employs widely
used techniques that are known to be helpful for neural machine translation, including iterative back-translation, selected finetuning, and ensemble. The final submission achieves the top BLEU for three translation directions.
We present our submissions to the WMT21 shared task in Unsupervised and Very Low Resource machine translation between German and Upper Sorbian, German and Lower Sorbian, and Russian and Chuvash. Our low-resource systems (German↔Upper Sorbian, Russian
↔Chuvash) are pre-trained on high-resource pairs of related languages. We fine-tune those systems using the available authentic parallel data and improve by iterated back-translation. The unsupervised German↔Lower Sorbian system is initialized by the best Upper Sorbian system and improved by iterated back-translation using monolingual data only.
Chinese character decomposition has been used as a feature to enhance Machine Translation (MT) models, combining radicals into character and word level models. Recent work has investigated ideograph or stroke level embedding. However, questions remai
n about different decomposition levels of Chinese character representations, radical and strokes, best suited for MT. To investigate the impact of Chinese decomposition embedding in detail, i.e., radical, stroke, and intermediate levels, and how well these decompositions represent the meaning of the original character sequences, we carry out analysis with both automated and human evaluation of MT. Furthermore, we investigate if the combination of decomposed Multiword Expressions (MWEs) can enhance the model learning. MWE integration into MT has seen more than a decade of exploration. However, decomposed MWEs has not previously been explored.
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
