The semantic Web aims to provide to Web information with a well-defined meaning and make it understandable not only by humans but also by computers, thus allowing the automation, integration and reuse of high-quality information across different applications. However, current information retrieval mechanisms for semantic knowledge bases are intended to be only used by expert users. In this work, we propose a natural language interface that allows non-expert users the access to this kind of information through formulating queries in natural language. The present approach uses a domain-independent ontology model to represent the question's structure and context. Also, this model allows determination of the answer type expected by the user based on a proposed question classification. To prove the effectiveness of our approach, we have conducted an evaluation in the music domain using LinkedBrainz, an effort to provide the MusicBrainz information as structured data on the Web by means of Semantic Web technologies. Our proposal obtained encouraging results based on the F-measure metric, ranging from 0.74 to 0.82 for a corpus of questions generated by a group of real-world end users. © The Author(s) 2015.
Bibliographical noteKAUST Repository Item: Exported on 2020-10-01
Acknowledgements: Funding This work is a result of the research stay (19592/EE/14) funded by the ‘Fundación Séneca-Agencia de Ciencia y Tecnología de la Región de Murcia’ under the ‘Jiménez de la Espada - Programa de Movilidad, Cooperación e Internacionalización’ programme, within the II PCTIRM 2011-2014 framework. In addition, Mario Andrés Paredes-Valverde is supported by the National Council of Science and Technology (CONACyT) and the Mexican government.