conftrace_

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 - Artificial Intelligence and Natural Language Processing

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 Deep Learning > Learning Types > Self-Supervised Learning

Keywords

neural machine translation low-resource translation iterative training synthetic parallel data monolingual data

More from ACL 2018

All ACL 2018 papers →

Low-Resource Machine Transliteration Using Recurrent Neural Networks of Asian Languages

Findings of the Second Workshop on Neural Machine Translation and Generation

A Shared Attention Mechanism for Interpretation of Neural Automatic Post-Editing Systems

Inducing Grammars with and for Neural Machine Translation

Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation

Controllable Abstractive Summarization