Scheduled Multi-Task Learning: From Syntax to Translation
Published
2018-04-24
Eliyahu Kiperwasser
,
Miguel Ballesteros
Eliyahu Kiperwasser
Bar-Ilan University
Miguel Ballesteros
IBM Research
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)