A Machine-Oriented Text Understanding Framework Based on Human Memory and Reading Process

With the rapid development of the Web, information on the Web, especially for textual information, has come to an extremely large amount and increases very fast every day. It has become much more difficult for people to find their interested or demanded information from the Web. Thus how to automatically and intelligently acquire the textual semantics from the Web has become an increasingly important issue today. In this paper, based on human memory and reading process, we propose a machine-oriented text understanding framework, which can guide machines to read texts with human ways so as to effectively acquire the semantics in texts and then further help people to find out the proper information they want. The proposed framework is on the basis of different kinds of memory systems in cognitive psychology and accordingly consists of four main parts, including shallow semantics acquiring model (SSAM), shallow-deep semantics processing model (SDSPM), episodic semantics activating model (ESAM) and background knowledge activating model (BKAM). A case study has been carried out to further specify the proposed framework.