Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLISN @ WMT 2021
Lisn @ WMT 2021
124
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة تقديم طلبات Lisn إلى مهمتين مشتركين في WMT'21.بالنسبة لمهمة الترجمة الطبية الحيوية، قمنا بتطوير أنظمة ثقيلة من الموارد للزوج اللغوي الإنجليزي - الفرنسي، باستخدام كلا من خارج المجال والمناطق في المجال.يتوافق النوع المستهدف لهذه المهمة (الملخصات العلمية) بالنصوص التي غالبا ما يكون لها هيكل موحد.تحاول أنظمتنا أن تأخذ هذا الهيكل في الاعتبار باستخدام نظام هرمي لعلامات مستوى الجملة.كما تم إعداد أنظمة الترجمة المهمة الإخبارية لزوج اللغة الفرنسية الألمانية.كان التحدي هو إجراء التكيف غير المزدوج مع المجال المستهدف (الأخبار المالية).لهذا، استكشفنا إمكانات الاستراتيجيات القائمة على الاسترجاع، حيث يتم استخدام الجمل التي تشبه مثيلات الاختبار لزيادة وحدة فك الترميز.
This paper describes LISN's submissions to two shared tasks at WMT'21. For the biomedical translation task, we have developed resource-heavy systems for the English-French language pair, using both out-of-domain and in-domain corpora. The target genre for this task (scientific abstracts) corresponds to texts that often have a standardized structure. Our systems attempt to take this structure into account using a hierarchical system of sentence-level tags. Translation systems were also prepared for the News task for the French-German language pair. The challenge was to perform unsupervised adaptation to the target domain (financial news). For this, we explored the potential of retrieval-based strategies, where sentences that are similar to test instances are used to prime the decoder.
References used
https://aclanthology.org/
rate research
Read More
This paper describes SYSTRAN submissions to the WMT 2021 terminology shared task. We participate in the English-to-French translation direction with a standard Transformer neural machine translation network that we enhance with the ability to dynamic
ally include terminology constraints, a very common industrial practice. Two state-of-the-art terminology insertion methods are evaluated based (i) on the use of placeholders complemented with morphosyntactic annotation and (ii) on the use of target constraints injected in the source stream. Results show the suitability of the presented approaches in the evaluated scenario where terminology is used in a system trained on generic data only.
The paper describes the 3 NMT models submitted by the eTranslation team to the WMT 2021 news translation shared task. We developed systems in language pairs that are actively used in the European Commission's eTranslation service. In the WMT news tas
k, recent years have seen a steady increase in the need for computational resources to train deep and complex architectures to produce competitive systems. We took a different approach and explored alternative strategies focusing on data selection and filtering to improve the performance of baseline systems. In the domain constrained task for the French--German language pair our approach resulted in the best system by a significant margin in BLEU. For the other two systems (English--German and English-Czech) we tried to build competitive models using standard best practices.
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.
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task. We participated in all of the three sub-tasks, including Sentence-Level Direct Assessment (DA) task, Word and Sentence-Level Post-editing Effort task and Critical Error Det
ection task, in all language pairs. Our systems employ the framework of Predictor-Estimator, concretely with a pre-trained XLM-Roberta as Predictor and task-specific classifier or regressor as Estimator. For all tasks, we improve our systems by incorporating post-edit sentence or additional high-quality translation sentence in the way of multitask learning or encoding it with predictors directly. Moreover, in zero-shot setting, our data augmentation strategy based on Monte-Carlo Dropout brings up significant improvement on DA sub-task. Notably, our submissions achieve remarkable results over all tasks.
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
