Analysis of some database schemas used to evaluate natural language interfaces to databases

Abstract

Most research work about the development of Natural Language Interface to Databases (NLIDB) has been focused on the study of the interpretation and translation from natural language queries to SQL queries. For this purpose and in order to improve the performance in a NLIDB, researchers have addressed different issues related to natural language processing. In addition to this, we consider that the performance of a NLIDB also depends on its ability to adapt to a database schema. For this reason, we analyzed the Geobase, ATIS and Northwind database schemas, commonly used to evaluate NLIDBs. As a result of this analysis, we present in this paper some issues arising from the three database schemas analyzed, which they should be considered in the implementation of a NLIDB to improve its performance.