Abstract

Abstract Recently, many question answering systems that derive answers from linked data repositories have been developed. The purpose of this survey is to identify the common features and approaches of the semantic question answering (SQA) systems, although many different and prototype systems have been designed. The SQA systems use a formal query language like SPARQL and knowledge of a specific vocabulary. This paper analyses different frameworks, architectures, or systems that perform SQA and classifies SQA systems based on different criteria.

Highlights

  • Serious efforts have been made to organize both general and specialized knowledge in the form of Resource Description Framework (RDF) knowledge bases (KBs) (Mazzeo & Zaniolo, 2016a)

  • Users ask questions in natural language using their own terminology and receive a response generated by searching in an RDF KB

  • Many prototype semantic question answering (SQA) systems have been developed for different datasets

Read more

Summary

Introduction

Serious efforts have been made to organize both general and specialized knowledge in the form of Resource Description Framework (RDF) knowledge bases (KBs) (Mazzeo & Zaniolo, 2016a). According to Bouziane et al (2015), the three basic components are as follows: Question Analysis (included classification and extraction, extended keywords, and Named Entity Recognition), Document Retrieval, and Answer Extraction which are included in most QA systems These components may have differences due to their implementation of every component. A solution to this problem is semantic question answering (SQA) systems In these systems, users ask questions in natural language using their own terminology and receive a response generated by searching in an RDF KB. Through semantic question answering (SQA) systems, users overcome two major barriers: using a dedicated query language, such as SPARQL, and having a perfect knowledge of the KB specific vocabulary (Höffner et al, 2017).

Related work
Classification based on types of analysis done on questions
Discussion and conclusions
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.