ClusTex: Information Extraction from HTML Pages

This paper propose ClusTex, a system which employs clustering techniques for automatic information extraction from HTML documents containing semi- structured data. Using domain-specific information provided by the user, ClusTex parses and tokenizes the data from an HTML document, partitions it into clusters containing similar elements, and estimates an extraction rule based on the pattern of occurrence of data tokens. The extraction rule is then used to refine clusters, and finally the output is reported. To demonstrate the effectiveness of this approach, the proposed approach is tested by conducting experiments on the University of Calgary Web-site; the results prove comparable to those reported in the literature.