Skip to main navigation menu Skip to main content Skip to site footer

Scheduled Multi-Task Learning: From Syntax to Translation

Abstract

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 and gradually puts 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.
Article at MIT Press PDF (presented at ACL 2018)