Conference Proceedings

A Stochastic Decoder for Neural Machine Translation

Trevor Cohn, Philip Schulz, Wilker Aziz

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers | ACL Anthology | Published : 2018


The process of translation is ambiguous, in that there are typically many valid translations for a given sentence. This gives rise to significant variation in parallel corpora, however, most current models of machine translation do not account for this variation, instead treating the problem as a deterministic process. To this end, we present a deep generative model of machine translation which incorporates a chain of latent variables, in order to account for local lexical and syntactic variation in parallel corpora. We provide an in-depth analysis of the pitfalls encountered in variational inference for training deep generative models. Experiments on several different language pairs demonst..

View full abstract

Citation metrics