Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFindings of the WMT 2021 Shared Tasks in Unsupervised MT and Very Low Resource Supervised MT
نتائج المهام المشتركة WMT 2021 في MT غير الخاضعة للإشراف والموارد منخفضة للغاية
315
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقدم نتائج المهام المشتركة WMT2021 في MT غير المنضدة والموارد منخفضة للغاية.في هذه المهمة، درس المجتمع ترجمة الموارد المنخفضة جدا بين اللغة الألمانية والصربية العليا، والترجمة غير المنخفضة بين الترجمة من اللغة الألمانية والسوربية والمنخفضة الموارد بين الروسية والجواد، وجميع لغات الأقليات مع المجتمعات اللغوية النشطة تعمل على الحفاظ على اللغات، والذين هم شركاء فيالتقييم.شكرا بذلك، تمكنا من الحصول على معظم البيانات الرقمية المتاحة لهذه اللغات وتقديمها للمشاركين في المهام.في المجموع، شارك ست فرق في المهمة المشتركة.تناقش الورقة الخلفية، وتعرض المهام والنتائج، ويناقش أفضل الممارسات للمستقبل.
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.
References used
https://aclanthology.org/
rate research
Read More
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.
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 report the results of the WMT 2021 shared task on Quality Estimation, where the challenge is to predict the quality of the output of neural machine translation systems at the word and sentence levels. This edition focused on two main novel additio
ns: (i) prediction for unseen languages, i.e. zero-shot settings, and (ii) prediction of sentences with catastrophic errors. In addition, new data was released for a number of languages, especially post-edited data. Participating teams from 19 institutions submitted altogether 1263 systems to different task variants and language pairs.
The machine translation efficiency task challenges participants to make their systems faster and smaller with minimal impact on translation quality. How much quality to sacrifice for efficiency depends upon the application, so participants were encou
raged to make multiple submissions covering the space of trade-offs. In total, there were 53 submissions by 4 teams. There were GPU, single-core CPU, and multi-core CPU hardware tracks as well as batched throughput or single-sentence latency conditions. Submissions showed hundreds of millions of words can be translated for a dollar, average latency is 5--17 ms, and models fit in 7.5--150 MB.
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
