Keyword question answering system with report generation for linked data

Author

Sangdo Han ; Hyosup Shim ; Byungsoo Kim ; Seonyeong Park ; Seonghan Ryu ; Lee, Gary Geunbae

fYear

2015

fDate

9-11 Feb. 2015

Firstpage

23

Lastpage

26

Abstract

We introduce a question-answering system that responds to a keywords-query by extracting information from linked data and generating reports in natural language (NL). Using entity disambiguation and distributed word similarity, we matched each keyword to a related entity and property in linked data. To extract keyword-related information, we used the entity and property to generate a SPARQL query. NL generation was performed using a NL generation template database. In our experiment, our system answered 95.1% of the user keyword questions in reasonable NL report.

Keywords

SQL; natural language processing; query processing; question answering (information retrieval); text analysis; NL report generation template database; SPARQL query; distributed word similarity; entity disambiguation; keyword matching; keyword question answering system; keyword-query; keyword-related information extraction; linked data; natural language; user keyword questions; Data mining; Databases; Encyclopedias; Knowledge discovery; Natural languages; Resource description framework; Semantics; QA system; keyword system; linked data; natural language generation; query generation; question answering system; report generation;

fLanguage

English

Publisher

ieee

Conference_Titel

Big Data and Smart Computing (BigComp), 2015 International Conference on

Conference_Location

Jeju

Type

conf

DOI

10.1109/35021BIGCOMP.2015.7072843

Filename

7072843