Chinese-Naxi syntactic statistical machine translation based on tree-to-tree

Abstract

For the purpose of using Naxi syntax information efficiently, we put forward a method of Chinese-Naxi syntactic statistical machine translation based on the tree-to-tree model. Firstly, for using syntax information of source language and target language, collecting Chinese-Naxi aligned parallel corpus and making a syntax parsing on both side, the method obtains corresponding phrase structure trees of Chinese and Naxi. Then, by using GMKH algorithm to extract a large number of translation rules between Chinese treelets and Naxi treelets, inferring their probabilistic relationship from these rules, it obtains the translation templates. Finally, using these translation templates, through a tree-parsing algorithm, to guide the decoding, translating each Chinese phrase treelet in bottom-up, it obtains the final translation text. In comparison with the tree-to-string model, the experiments show that this method improves 1.2 BLEU value. This proves that both Chinese syntactic information and Naxi syntactic information are very helpful in improving the performance of Chinese-Naxi machine translation.