Neural Machine Translation with Pivot Languages

Abstract

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. We propose three methods to connect the two models and enable them to interact with each other during training. Experiments on Europarl and WMT corpora show that joint training of source-to-pivot and pivot-to-target models leads to significant improvements over independent training across various languages.

fix experiments and revise the paper

References in corpus (2)

• On Using Monolingual Corpora in Neural Machine Translation
• Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions

Cited by in corpus (4)

• Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
• Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
• Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT
• Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages