papers AI Learner
The Github is limit! Click to go to the new site.

Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT

2018-05-11
Danielle Saunders, Felix Stahlberg, Adria de Gispert, Bill Byrne

Abstract

We explore strategies for incorporating target syntax into Neural Machine Translation. We specifically focus on syntax in ensembles containing multiple sentence representations. We formulate beam search over such ensembles using WFSTs, and describe a delayed SGD update training procedure that is especially effective for long representations like linearized syntax. Our approach gives state-of-the-art performance on a difficult Japanese-English task.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1805.00456

PDF

https://arxiv.org/pdf/1805.00456


Comments

Content