【摘要】 知识抽取主要研究如何从无语义信息的文档内容中抽取与本体匹配的事实知识,进而实现对Web数据充分、有效的利用,已经成为国内外语义Web领域的研究热点之一。介绍了知识抽取相关技术知识,系统地分析比较了面向英文和中文的知识抽取方法,着重探讨了对中文自然语言文档内容的自动知识抽取方法,指出了目前该类方法的不足,并展望了知识抽取发展的方向。更多还原

【Abstract】 Knowledge extraction,whose main task is to extract the factual knowledge from the no-semantics-embedded documents and to realize the full and effective use of Web data,has become a hot topic in the semantic Web field. Firstly,this paper gave a brief introduction of knowledge extraction related technologies. Secondly,analyzed and compared the English-oriented and Chinese-oriented knowledge extraction methods systematically,especially the methods towards Chinese natural language documents. Lastly,pointed out the main drawbacks of the current methods and discussed the future development direction of knowledge extraction.更多还原