Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
arXiv:1904.02331
Abstract
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo sentence pairs are generated to train the models with a reconstruction loss. However, the pseudo sentences are usually of low quality as translation errors accumulate during training. To avoid this fundamental issue, we propose an alternative but more effective approach, extract-edit, to extract and then edit real sentences from the target monolingual corpora. Furthermore, we introduce a comparative translation loss to evaluate the translated target sentences and thus train the unsupervised translation systems. Experiments show that the proposed approach consistently outperforms the previous state-of-the-art unsupervised machine translation systems across two benchmarks (English-French and English-German) and two low-resource language pairs (English-Romanian and English-Russian) by more than 2 (up to 3.63) BLEU points.
arXiv comment11 pages, 3 figures. Accepted to NAACL 2019
References in corpus (6)
- Sequence to Sequence Learning with Neural Networks
- Dual Learning for Machine Translation
- On Using Monolingual Corpora in Neural Machine Translation
- Adversarial Ranking for Language Generation
- A Retrieve-and-Edit Framework for Predicting Structured Outputs
- Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems