Decoding Optimization for Chinese-English Machine Translation via a Dependent Syntax Language Model

摘要

Decoding is a core process of the statistical machine translation, and determines the final results of it. In this paper, a decoding optimization for Chinese-English SMT with a dependent syntax language model was proposed, in order to improve the performance of the decoder in Chinese-English statistical machine translation. The data set was firstly trained in a dependent language model, and then calculated scores of NBEST list from decoding with the model. According to adding the original score of NBEST list from the decoder, the NBEST list of machine translation was reordered. The experimental results show that this approach can optimize the decoder results, and to some extent, improve the translation quality of the machine translation system.