Natural Language Querying System Through Entity Enrichment

Abstract

This paper focuses on a domain expert querying system over databases. It presents a solution designed for a French enterprise interested in offering a natural language interface for its clients. The approach, based on entity enrichment, aims at translating natural language queries into database queries. In this paper, the database is treated through a logical paradigm, suggesting the adaptability of our approach to different database models. The good precision of our method is shown through some preliminary experiments.

Figures (3)

• Figure 1: Dependency tree and POS tagging
• Figure 2: Auxiliary structures built in the pre-processing phase
• Figure 3: Simple entities extracted from $NLQ_{run}$