부산대학교 도서관

This paper presents a proposal for automatically detecting the structure of regulatory documents, tagging management and text segmentation in units able to be processed as entries in a database. The information stored in that way must be adequate to be efficiently managed by a chatter bot named PTAH, which aims to answer user questions in Natural Language. As part of this work, the usage, main difficulties and characteristics of managing the information in this context is explained. Then, there is a step by step derivation using the proposed method with a small test set of 27 documents. Finally, the results are analyzed and evaluated. The proposal is flexible and robust, based on simple processing, clustering and a rule-based automatic algorithm.