An Evolutionary Genre-Based and Domain-Independent Approach for High-Level Knowledge Discovery from Texts

Mining Answers from Texts and Knowledge Bases

Volume

Papers from the 2002 AAAI Spring Symposium

Contents

in this ongoing research, an integrated approach for discovering high-level knowledge from texts by exploiting both local (contextual) information and global hypotheses is proposed. The underlying model which integrates Information Extraction and evolutionary techniques to produce interesting and novel hypotheses rules is described. In addition, novel criteria to evaluate the roles’ performance in terms of interestingness and novelty are proposed.