Scheduled Multi-Task Learning: From Syntax to Translation
This work addresses translation quality for machine learning practitioners, but it is incremental as it builds on existing encoder-decoder models.
The paper tackled the problem of improving neural machine translation by integrating syntax learning into the training process, achieving considerable BLEU score improvements on both large and low-resource datasets.
Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework in which our model begins learning syntax and translation interleaved, gradually putting more focus on translation. Using this approach, we achieve considerable improvements in terms of BLEU score on relatively large parallel corpus (WMT14 English to German) and a low-resource (WIT German to English) setup.