Database semantics representation for natural language access

Abstract

In natural language database interfaces (NLDBI), manual construction of translation knowledge normally undermines domain portability because of its expensive human intervention. To overcome this, this paper proposes linguistically-motivated database semantics in order to systematically construct translation knowledge. Database semantics consists of two structures which are designed to function as a translation dictionary, and to contain selectional restriction constraints on domain classes. The database semantics is semi-automatically obtained from a semantic data model for a target database. Based on this database semantics, a conceptual NLDBI translation scheme is developed. Translating a natural language question into a database query suffers from the translation ambiguity problem, which has not received significant attention in this field. To deal with translation ambiguity, we suggest an ambiguity resolution method based on the proposed database semantics. Experiments showed the usefulness of the proposed database semantics and its disambiguation procedures.