Refinements of machine translation by automatic editorial operations

摘要

The performance of state-of-the-art machine translation (MT) systems is still far from being perfect. In this article, we investigate the combination of on-line MT systems to produce better outputs. The basic idea is to apply editorial operations of substitution, insertion, and deletion to candidate outputs in an automatic fashion. The proposed methods are evaluated on the translation task in the travel domain from Chinese to English as defined in the International Workshop on Spoken Language Translation evaluation campaign. Outputs of three on-line MT engines are combined. The proposed method is evaluated on Chinese-to-English MT tasks in the tourism domain. An overall improvement of 1.4 in the BLEU score over the best single-system baseline has been achieved.