Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization
Jiacheng Zhang, Yang Liu, Huanbo Luan, Jingfang Xu, Maosong Sun · 2017
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.