Recurrent Neural Network based Translation Quality Estimation

This paper describes the recurrent neural network based model for translation quality estimation. Recurrent neural network based quality estimation model consists of two parts. The first part using two bidirectional recurrent neural networks generates the quality information about whether each word in translation is properly translated. The second part using another recurrent neural network predicts the final quality of translation. We apply this model to sentence, word and phrase level of WMT16 Quality Estimation Shared Task. Our results achieve the excellent performance especially in sentence and phraselevel QE.