pith. sign in

arxiv: 1805.10844 · v1 · pith:L2TYDJ47new · submitted 2018-05-28 · 📊 stat.ML · cs.CL· cs.LG

A Stochastic Decoder for Neural Machine Translation

classification 📊 stat.ML cs.CLcs.LG
keywords translationmachinedeepgenerativemodelmodelsparallelprocess
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.