The word order between source and target languages significantly influences the translation quality in machine translation. Preordering can effectively address this problem. Previous preordering methods require a manual feature design, making language dependent design costly. In this paper, we propose a preordering method with a recursive neural network that learns features from raw inputs. Experiments show that the proposed method achieves comparable gain in translation quality to the state-of-the-art method but without a manual feature design. 1 In this paper, we used binary syntax trees.

The difference in word orders between source and target languages is a serious hurdle for machine translation. Preordering methods, which reorder the words in a source sentence before translation to obtain a similar word ordering with a target language, significantly improve the quality in statistical machine translation. While the information on the preordering position improved the translation quality in recurrent neural network-based models, questions such as how to use preordering information and whether it is helpful for the Transformer model remain unaddressed. In this paper, we successfully employed preordering techniques in the Transformer-based neural machine translation. Specifically, we proposed a novel preordering encoding that exploits the reordering information of the source and target sentences as positional encoding in the Transformer model. Experimental results on ASPEC Japanese-English and WMT 2015 English-German, English-Czech, and English-Russian translation tasks confirmed that the proposed method significantly improved the translation quality evaluated by the BLEU scores of the Transformer model by 1.34 points in the Japanese-to-English task, 2.19 points in the English-to-German task, 0.15 points in the Czech-to-English task, and 1.48 points in the English-to-Russian task.

No 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.