← Back to papers
2021 EMNLP EMNLP 2021

LISN @ WMT 2021

Abstract

AbstractThis 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.

🌉 Interdisciplinary Bridge — Deep Learning and Healthcare & Medicine and Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — retrieval-based priming
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Jitao Xu , Minh Quang Pham , Sadaf Abdul Rauf , François Yvon

Topics

Natural Language Processing > Applications > Machine Translation Natural Language Processing > Generation > Machine Translation Machine Learning > Learning Types > Domain Adaptation Healthcare & Medicine > Clinical > Medical AI Deep Learning > Models > Transformers Machine Learning > Learning Types > Machine Translation

Keywords

transformer architecture domain adaptation machine translation neural machine translation bleu score biomedical translation hierarchical tagging retrieval-based priming retrieval-based translation
Download PDF

Related papers

Continual Learning in Multilingual NMT via Language-Specific Embeddings 2021
MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents 2021
Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity 2021
Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings 2021
Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis 2021