Neural Machine Translation with Pivot Languages
This addresses translation challenges for low-resource languages, though it is incremental as it builds on existing pivot methods.
The paper tackles the data scarcity problem in neural machine translation for resource-scarce language pairs by introducing a joint training algorithm for pivot-based models, showing significant improvements over independent training on Europarl and WMT corpora.
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.