NATURAL LANGUAGE QUESTION ANSWERING SYSTEM OVER LINKED DATA
Abstract
Linked Data project is aimed to give more details on any subject through the big knowledge bases defined on the web. In this context, knowledge bases offer endpoint service user interfaces to query their data. Because of the SPARQL query language limitation of these knowledge bases, a significant number of web users are unable to benefit from these services. In this paper, an English natural language question answering system over Linked Data is proposed in order to eliminate this limitation. The proposed system's main processes can be listed as follows: (1) Extracting Part-Of-Speech (POS) tags, (2) pattern extraction & preparing appropriate SPARQL queries, (3) executing user queries & displaying the results. The features which are not provided by the endpoint services of knowledge bases such as dynamic paging, voice search and answer vocalization which make the usage of the proposed system to be possible by the visually-impaired web users, question-answer caching, social media integration, and live spell checking are proposed. According to experimental results, the proposed system’s question answering performance is improved between 2 and 12 times through the type of natural language question thanks to the question-answer caching mechanism.
Keywords
DBpedia,Natural Language Processing,Speech Recognition,Semantic Web
References
- [1] Berners-Lee T, Hendler J, Lassila O. The Semantic Web. Sci Am Citeseer 2001; 284(5):34–43.
- [2] Metz C. Tim, Lucy, and The Semantic Web. PC Mag 2007.
- [3] Rapoza J. SPARQL Will Make the Web Shine. eweek 2006.
- [4] Segaran T, Evans C, Taylor J. Programming the Semantic Web. 1st ed. Sebastopol, CA, USA: O’Reilly Media, 2009.
- [5] Bizer C, Heath T, Berners-Lee T. Linked data-the story so far. Int J Semant Web Inf Syst 2009; 5 (3):1–22.
- [6] Doncel VR. How O is the LOD cloud? 2015. Available at: http://www.cosasbuenas.es/blog/how-o-is-lod-2015; Accessed: 10-Jun-2018.
- [7] State of the LOD Cloud. University of Mannheim 2015. Available at: http://linkeddatacatalog.dws.informatik.uni-mannheim.de/state/; Accessed: 12-May-2019.
- [8] Linked Open Data cloud diagram as of March 2019. Linked Open Cloud 2019. Available at: https://lod-cloud.net/versions/2019-03-29/lod-cloud.png; Accessed: 12-May-2019.
- [9] Lehmann J, Schüppel J, Auer S. Discovering Unknown Connections – the DBpedia Relationship Finder. In: Proceedings of the 1st SABRE Conference on Social Semantic Web - CSSW’07; 26-28 September 2007; Leipzig, Germany.
- [10] Kabakus AT, Dogdu E. Question Answering System over Linked Data. In: 7th National Software Engineering UYMS’13; 26 September 2013; İzmir, Turkey.