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.
@article{arxiv.1811.01100,
title = {Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization},
author = {Jiacheng Zhang and Yang Liu and Huanbo Luan and Jingfang Xu and Maosong Sun},
journal= {arXiv preprint arXiv:1811.01100},
year = {2018}
}