SIIPU*S: A Semantic Pattern Learning Algorithm

The efficacy of pattern-based question answering system is mostly determined by the size of the semantic pattern base and the expression capability of the semantic patterns. We find that the expression capabilities of semantic patterns are determined by their instantiation degrees. Hence, we propose an evaluation strategy named Semantic Identifiability Inverse Pattern Universality (SIIPU), using which we can estimate the instantiation degree of a pattern for a certain semantic requirement. Moreover, on the basis of SIIPU, we propose a semantic pattern learning algorithm named SIIPU*S. Using SIIPU*S we can extract the semantic patterns at the most appropriate instantiation level for a given semantic requirement from a training corpus. Preliminary results show the proposed method´s efficacy to extract patterns at different instantiation levels and their effects in analyzing questions.