NATURAL LANGUAGE QUESTION ANSWERING SYSTEM OVER LINKED DATA

Authors : Abdullah Talha KABAKUŞ, Aydın ÇETİN

Pages : 274-295

Doi:10.18038/estubtda.624498

View : 18 | Download : 12

Publication Date : 2019-09-26

Article Type : Research Paper

Abstract :Normal 0 21 false false false TR X-NONE X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:`Normal Tablo`; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:``; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin-top:0cm; mso-para-margin-right:0cm; mso-para-margin-bottom:8.0pt; mso-para-margin-left:0cm; line-height:107%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:`Calibri`,sans-serif; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-fareast-language:EN-US;} 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: insert ignore into journalissuearticles values(1); Extracting Part-Of-Speech insert ignore into journalissuearticles values(POS); tags, insert ignore into journalissuearticles values(2); pattern extraction & preparing appropriate SPARQL queries, insert ignore into journalissuearticles values(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