基于Word Net和How Net建设双语语义词典

Building Bi-lingual Semantic Lexicons Based on WordNet and HowNet

针对当前语义信息往往需要手工获取的现状 ,探讨了利用英语义类词典Word Net和汉语概念词典HowNet资源 ,为双语机读词典ECDic2K的英语词条添加概念和语义类的自动方法 ,以改善手工添加语义类带来的低效率和不一致性等问题。实验表明 ,该方法向英汉双语机读词典ECDic2K的 35 84 8词条译文项自动添加语义信息 ,而改造后的双语语义词典为单语语义分析中的成熟技术用于跨语言研究提供了方便 ,这在机器翻译和跨语言检索等自然语言处理领域具有很高的实用价值。

An automatic approach based on the famous thesaurus of WordNet and HowNet is presented to add semantic information to the English Chinese dictionary ECDic2K of the machine translation system. Compared with the manual approach to constructing bi-lingual dictionaries, this method is more efficient and consistent. With this method, 35848 semantic items are successfully added to the ECDic2K. The semantic information in the dictionary makes it possible to apply the advanced techniques of mono-lingual semantic analysis to the field of cross-language research. And so, it is of great significance in natural language processing tasks, such as machine translation, cross-language information retrieval and so on.