English

A Stochastic Decoder for Neural Machine Translation

Machine Learning 2018-05-29 v1 Computation and Language Machine Learning

Abstract

The process of translation is ambiguous, in that there are typically many valid trans- lations for a given sentence. This gives rise to significant variation in parallel cor- pora, however, most current models of machine translation do not account for this variation, instead treating the prob- lem 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 ac- count for local lexical and syntactic varia- tion in parallel corpora. We provide an in- depth analysis of the pitfalls encountered in variational inference for training deep generative models. Experiments on sev- eral different language pairs demonstrate that the model consistently improves over strong baselines.

Keywords

Cite

@article{arxiv.1805.10844,
  title  = {A Stochastic Decoder for Neural Machine Translation},
  author = {Philip Schulz and Wilker Aziz and Trevor Cohn},
  journal= {arXiv preprint arXiv:1805.10844},
  year   = {2018}
}

Comments

Accepted at ACL 2018

R2 v1 2026-06-23T02:10:14.909Z