Answering N-Relation Natural Language Questions in the Commercial Domain

This paper presents SynchroBot, a Natural Language Question Answering system in the Commercial Domain. It relies on an RDF dataset and an RDFS ontology that we have developed for the commercial domain of the mobile phone industry. We propose an approach to understand and interpret natural language questions, based on the use of regular expressions to identify both the properties connecting entities, and their values. These regex are automatically learned from a subset of our dataset with a genetic algorithm.