← Back to papers
2021 EMNLP EMNLP 2021

CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT

Abstract

AbstractWe describe our two NMT systems submitted to the WMT2021 shared task in English-Czech news translation: CUNI-DocTransformer (document-level CUBBITT) and CUNI-Marian-Baselines. We improve the former with a better sentence-segmentation pre-processing and a post-processing for fixing errors in numbers and units. We use the latter for experiments with various backtranslation techniques.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — backtranslation technique
🐝 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, Security & Privacy, Speech & Audio

Authors

Petr Gebauer , Ondřej Bojar , Vojtěch Švandelík , Martin Popel

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Deep Learning > Learning Types > Transfer Learning Machine Learning > Learning Types > Machine Translation

Keywords

neural machine translation document-level translation sentence segmentation transformer model backtranslation technique
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