FREyA: An Interactive Way of Querying Linked Data Using Natural Language

摘要

Natural Language Interfaces are increasingly relevant for in formation systems fronting rich structured data stores such as RDF and OWL repositories, mainly because of the conception of them being intu itive for human. In the previous work, we developed FREyA, an interac tive Natural Language Interface for querying ontologies. It uses syntactic parsing in combination with the ontology-based lookup in order to inter pret the question, and involves the user if necessary. The user's choices are used for training the system in order to improve its performance over time. In this paper, we discuss the suitability of FREyA to query the Linked Open Data. We report its performance in terms of precision and recall using the MusicBrainz and DBpedia datasets.