Machine transliteration using multiple transliteration engines and hypothesis re-ranking
Machine transliteration using multiple transliteration engines and hypothesis re-ranking
复制标题
使用多个音译引擎的机器音译和假设重新排序
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
H. Isahara
中科院分区：
文献类型：
--
作者：
Jong;H. Isahara
本文提出了一种新的方法，通过使用多个音译假设和重新排序，以改善机器音译。我们建立了七个机器音译引擎，以产生一组音译假设。然后，我们重新排列假设，以选择正确的音译假设。我们提出了一种重新排序的方法，利用置信度分数，语言模型和Web频率的功能，并将它们与机器学习算法，包括支持向量机和最大熵模型相结合。我们对英语到日语和英语到韩语的音译的测试表明，我们的方法中使用的单个翻译引擎与以前的方法相比表现出色，并且与最好的单个引擎相比，重新排名将单词准确率从65%提高到88%。
This paper describes a novel method of improving machine transliteration by using multiple transliteration hypotheses and re-ranking them. We constructed seven machine-transliteration engines to produce a set of transliteration hypotheses. We then re-ranked the hypotheses to select the correct transliteration hypothesis. We propose a re-ranking method that makes use of confidence-score, language-model, and Web-frequency features and combines them with machine-learning algorithms including support vector machines and the maximum entropy model. Our testing of English-to-Japanese and English-to-Korean transliterations revealed that the individual translit-eration engines used in our approach performed comparably to previous approaches and that re-ranking improved word accuracy compared to the best individual engine from about 65 to 88%.