跨语言信息检索中的命名实体识别与翻译

The Extraction and Translation of Named Entity in Cross Language Information Retrieval

综述命名实体识别与翻译研究现状,提出基于信息抽取的命名实体识别与翻译方法,以及对该方法进行一系列集成优化处理,并实现了基于命名实体识别与翻译的跨语言信息检索实验。实验结果显示出命名实体识别与翻译在跨语言信息检索中的重要性,并证明了所提出的翻译加权和网络挖掘未登录命名实体方法的应用能显著提高跨语言信息检索的性能。

In this article,we survey the current research on the named entity（NE） recognition and translation,propose an information extraction-based module for NE recognition and translation,put some integrated enhancement methods on NE translation,and integrate the module into a cross-language information retrieval（CLIR） system.Then we conduct experiments to examine the effectiveness of the integrated module in CLIR.The experiment results show that recognizing and translating named entities plays important role in CLIR,and our methods of weighting translations and mining translations on the Web for out of vocabulary named entities can significantly improve CLIR performance.