← Back to papers
2018 ACL ACL 2018

Iterative Back-Translation for Neural Machine Translation

Abstract

AbstractWe present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. We demonstrate improvements in neural machine translation quality in both high and low resourced scenarios, including the best reported BLEU scores for the WMT 2017 German↔English tasks.

🌉 Interdisciplinary Bridge — Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — synthetic parallel datum
🐣 Hot Topic Early Bird — neural machine translation
🐝 Cross-Pollinator — Artificial Intelligence, Deep Learning, Machine Learning, Natural Language Processing, Speech & Audio

Authors

Vu Cong Duy Hoang , Philipp Koehn , Gholamreza Haffari , Trevor Cohn

Topics

Machine Learning > Learning Types > Semi-Supervised Learning Machine Learning > Application Areas > Data Augmentation Natural Language Processing > Applications > Machine Translation Natural Language Processing > Generation > Machine Translation Deep Learning > Learning Types > Self-Supervised Learning

Keywords

neural machine translation low-resource translation iterative training synthetic parallel datum monolingual datum
Download PDF

Related papers

Economic Event Detection in Company-Specific News Text 2018
Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus 2018
SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment 2018
Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer 2018
Affordances in Grounded Language Learning 2018