Recursive Neural Network-Based Preordering for Statistical Machine Translation and Its Analysis

Abstract

Word-order differences between source and target languages significantly affect statistical machine translation. This problem can be effectively addressed by preordering. A state-of-the-art preordering method would involve manually designed feature templates. In this paper, we propose a method that uses a recursive neural network that can learn end-to-end preordering. English-Japanese, English-French, and English-Chinese datasets are extensively evaluated. The results confirm that this method achieves an English-to-Japanese translation quality that is comparable with that of the state-of-the-art method, without manually designed feature templates. In addition, a detailed analysis examines the factors affecting preordering and translation quality as well as the effects of preordering in neural machine translation.