A Framework for Machine Translation Output Combination

A Framework for Machine Translation Output Combination

本研究提供一個線上機器翻譯整合系統整合三個不同的線上翻譯引擎。該翻譯整合系統，利用了選擇、替換、插入及刪除等模組，針對線上翻譯假說進行修正。我們實際整合了GOOGLE、YAHOO、譯言堂的翻譯假說。在IWSLT07的測試語料進行中文至英文的翻譯整合。由實驗結果得知，該翻譯整合系統其BLEU 分數由所整合的最佳翻譯系統的19.15 進步到20.55 。該翻譯整合系統相較於所整合的最佳線上翻譯系統進步了1.4 BLEU。

In this paper, we propose a framework for combining outputs from multiple on-line machine translation systems. This framework consists of several modules, including selection, substitution, insertion, and deletion. We evaluate the combination framework on IWSLT07 in travel domain, for the translation direction from Chinese to English. Three different on-line machine translation systems, Google, Yahoo, and TransWhiz, are used in the investigation. The experimental results show that our proposed combination framework improves BLEU score from 19.15 to 20.55. It achieves an absolute improvement of 1.4 in the BLEU score.