模糊语义模式及其在汉英机译系统英文生成选词中的应用

研究生成选词问题对改善机翻系统的翻译质量有重要意义, 基于语义模式的选词方法是常用的选词方法, 在混合选词模型也扮演了重要角色。本文针对该方法的不足, 提出了语义模式自动获取的思路和模糊语义模式的概念, 对其进行了改进。采用语义模式自动获取的思路可以克服传统手工方法需要巨大工作量的问题, 而模糊语义模式概念的提出则使语义模式能表示语言现象的量化差别。文中首先讨论该研究的重要性, 然后介绍了模糊语义模式的概念, 接着给出了构建模糊语义模式库时使用的一个训练算法, 最后给出了应用模糊语义模式进行选词的具体算法并将它与传统算法进行了比较。

Fuzzy Semantic Pattern and Its Application in the Lexical Selection for English Generation

Lexical selection for target language generation is important in improving the results of a machine translation system. The method basing on semantic patterns has been proved to be useful in resolving this problem. This paper presents an improvement of this method according to its shortcomings. The semantic patterns used in this system are named fuzzy semantics patterns. They are different from the traditional ones and will be trained from an example base with a training algorithm. In this paper, the format of fuzzy semantic patterns, the algorithm that acquiring fuzzy semantic patterns and the algorithm using fuzzy semantic patterns to perform lexical selection are all discussed in detail. First,We argue the importance to improve the traditional method. Then we introduce the concept of fuzzy semantic patterns. After that we show the algorithm that used to acquire fuzzy semantic patterns from examples. At last the algorithm of lexical selection using fuzzy semantic patterns is described.