Tag-less Back-Translation

Abstract

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard back-translation method has been shown to be unable to efficiently utilize the available huge amount of existing monolingual data because of the inability of translation models to differentiate between the authentic and synthetic parallel data during training. Tagging, or using gates, has been used to enable translation models to distinguish between synthetic and authentic data, improving standard back-translation and also enabling the use of iterative back-translation on language pairs that underperformed using standard back-translation. In this work, we approach back-translation as a domain adaptation problem, eliminating the need for explicit tagging. In the approach -- \emph{tag-less back-translation} -- the synthetic and authentic parallel data are treated as out-of-domain and in-domain data respectively and, through pre-training and fine-tuning, the translation model is shown to be able to learn more efficiently from them during training. Experimental results have shown that the approach outperforms the standard and tagged back-translation approaches on low resource English-Vietnamese and English-German neural machine translation.

arXiv comment29 pages, 4 figures, 13 tables

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Convolutional Sequence to Sequence Learning
• Language Modeling with Gated Convolutional Networks
• Sequence Level Training with Recurrent Neural Networks
• Dual Learning for Machine Translation
• Universal Transformers
• A Survey of Domain Adaptation for Neural Machine Translation
• Investigating Backtranslation in Neural Machine Translation
• Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation
• Trivial Transfer Learning for Low-Resource Neural Machine Translation
• Adaptation of Machine Translation Models with Back-translated Data using Transductive Data Selection Methods