we present a way of semantic modelling the elements that integrate the knowledge of a NLIDB, with the aim of
increasing the number of correctly-answered queries. To model the knowledge, we designed semantic representations in the
Ontology Web Language (OWL) in order to: a) model any relational database schema and its relationship with the natural
language, which it allows interpreting natural language queries and generating the corresponding SQL queries and b) add
metadata to natural language words to enable our NLIDB to interpret natural language queries that integrate superlatives, which
allows to increase the linguistic coverage of our NLIDB. In order to make the knowledge customization in our NLIDB easy for
the user, we implemented these semantic representations in a Customization Module (CM). To assess the performance of our
NLIDB, we configured it in a relational database that we migrated from Geobase and we used the Geoquery250 corpus [4, 5].
We compared its performance with the interfaces, ELF, Freya and NLP-Reduce. The results indicate that our proposal allowed
our NLIDB to obtain the best performance.
This paper is structured as follows: Section 2 presents related works; section 3 describes the design of the semantic
representations used to model the knowledge of our NLIDB; section 4 shows the description of the CM; section 5 provides an
example of the use of the semantic representations; section 6 presents the experimental results and section 7 presents the
conclusions drawn from this research.