Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization release_za4zbk7mwva4fem7frhl7roijq

by Jiacheng Zhang, Yang Liu, Huanbo Luan, Jingfang Xu, Maosong Sun

Released as a article .

2018  

Abstract

Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge. In this work, we propose to use posterior regularization to provide a general framework for integrating prior knowledge into neural machine translation. We represent prior knowledge sources as features in a log-linear model, which guides the learning process of the neural translation model. Experiments on Chinese-English translation show that our approach leads to significant improvements.
In text/plain format

Archived Files and Locations

application/pdf  187.3 kB
file_jdhxeydx6ndvfb5ihwhesjmm5i
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-11-02
Version   v1
Language   en ?
arXiv  1811.01100v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 9e4fd6d2-243a-4005-911c-c168b02662c9
API URL: JSON