A Prototype of Semantic-Based Intelligent Search Engine for Chinese Documents

To overcome the shortcomings of traditional search engines, advocates a prototype of semantic-based search engine, called CRAB. By combining technologies of semantic Web, information extraction (IE), natural language processing (NLP) and a novel theme-based method, this framework can extract factual knowledge from Chinese natural language documents automatically. Instead of list of document links, results of user´s query request returned from CRAB are semantically coherent reports generated intelligently, which can satisfy users greatly.