Rule acquisition by identifying rules from web pages

Abstract

In the world of Web pages, there are oceans of documents in natural language texts and tables. To extract rules from Web pages and maintain consistency between them, we have developed the framework of XRML (eXtensible Rule Markup Language). XRML allows the identification of rules on Web pages and generates the identified rules automatically. For this purpose, we have designed the Rule Identification Markup Language (RIML) that is similar to the formal Rule Structure Markup Language (RSML), both as parts of XRML. RIML is designed to identify rules not only from texts, but also from tables. The beauty of using RIML is that the rules can be identified on the Web pages and automatically transformed to the formal rules in RSML syntax. While designing RIML, we considered the features of sharing variables and values, omitted terms, and synonyms. Handling them in RIML is beneficial because they may be coded once and changed in the same place, automatically generating its corresponding RSML rules. We have conducted an experiment to evaluate the potential benefit of the XRML approach with the real world Web pages of Amazon.com, BarnesandNoble.com, and Powells.com. We found that 97.7% of the rules can be detected on the Web pages, and the completeness of generated rules is 89.7%. This is good proof that XRML can benefit the extraction and maintenance of rules from Web pages while building expert systems in the Semantic Web environment.