Abstract: Automatic knowledge extraction method can recognize and extract the factual knowledge on matching the ontology from the Web documents automatically. These factual knowledge can not only be used to implement knowledge-based services but also provide necessary semantic content to enable the realization of the vision of Semantic Web. However, it is very difficult to deal with the natural language documents, especially the Chinese natural language documents. This paper proposes a new knowledge extraction method (AKE) based on Semantic Web theory and Chinese natural language processing (NLP) technologies. This method uses aggregated knowledge concept to depict N-ary relation knowledge in ontology and can automatically extract not only the explicit but also the implicit simple and N-ary complex factual knowledge from Chinese natural language documents without using the large scale linguistics databases and synonym table. Experimental results show that this method is better than other similar methods.