Syntax-Augmented Machine Translation using Syntax-Label Clustering

Recently, syntactic information has helped significantly to improve statistical machine translation. However, the use of syntactic information may have a negative impact on the speed of translation because of the large number of rules, especially when syntax labels are projected from a parser in syntax-augmented machine translation. In this paper, we propose a syntax-label clustering method that uses an exchange algorithm in which syntax labels are clustered together to reduce the number of rules. The proposed method achieves clustering by directly maximizing the likelihood of synchronous rules, whereas previous work considered only the similarity of probabilistic distributions of labels. We tested the proposed method on Japanese-English and Chinese-English translation tasks and found order-of-magnitude higher clustering speeds for reducing labels and gains in translation quality compared with previous clustering method.