KIISE Transactions on Computing Practices (정보과학회 컴퓨팅의 실제 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Domain Question Answering System

도메인 질의응답 시스템

  • 윤승현 (삼성전자 소프트웨어센터) ;
  • 임은희 (삼성전자 소프트웨어센터) ;
  • 김덕호 (삼성전자 소프트웨어센터)
  • Received : 2014.09.12
  • Accepted : 2014.11.19
  • Published : 2015.02.15
⟨ Previous Next ⟩

Abstract

Question Answering (QA) services can provide exact answers to user questions written in natural language form. This research focuses on how to build a QA system for a specific domain area. Online and offline QA system architecture of targeted domain such as domain detection, question analysis, reasoning, information retrieval, filtering, answer extraction, re-ranking, and answer generation, as well as data preparation are presented herein. Test results with an official Frequently Asked Question (FAQ) set showed 68% accuracy of the top 1 and 77% accuracy of the top 5. The contribution of each part such as question analysis system, document search engine, knowledge graph engine and re-ranking module for achieving the final answer are also presented.

Question Answering (QA) 서비스는 사용자의 자연어 질의에 대응하는 정확한 답변을 제공하는 시스템이다. 본 연구는 특정 도메인에 관련한 사용자들의 질문에 대해 QA 서비스가 자동으로 대응하는 방법에 관한 연구이다. 이를 수행하기 위하여 사용자의 자연어 질문을 이해하고, 정형 데이터 및 비정형 데이터로부터 사용자 질문에 적합한 답변을 도출하여 제공하는 방법을 제시한다. 실험 결과 top 1 accuracy 68%, top 5 accuracy 77% 결과를 얻었다. 또한 본 논문은 QA 시스템 내부 모듈이 전체 accuracy에 미치는 영향에 대해서도 기술하였다.

Keywords

References

  1. Samsung Electronics. S-Voice. [Online]. Available: http://www.samsung.com/global/galaxys3/svoice.html
  2. Apple. Apple-iOS-Siri. [Online]. Available: https://www.apple.com/ios/siri
  3. Olafur Pall Geirsson, "IceQA: Developing a question answering system for Icelandic," [Online]. Available: http://kennarar.ru.is/hrafn/students/IceQA.pdf (downloaded 2015, Jan. 14)
  4. Apache. Lucene. [Online]. Available: http://lucene.apache.org
  5. Jun-Ping Ng, "QANUS: An Open-source Question-Answering Platform," [Online]. Available: http://www.comp.nus.edu.sg/-kanmy/papers/qanus.pdf (downloaded 2015, Jan. 14)
  6. Fan, J., "Automatic knowledge extraction from documents," IBM Journal of Research and Development, Vol. 56, Issue 3.4.
  7. J. Chu-Carroll, "Finding needles in the haystack : Search and candidate generation," IBM Journal of Research and Development, Vol. 56, Issue 3.4.
  8. D. A. Ferrucci, "Introduction to This is Watson," IBM Journal of Research and Development, Vol. 56, Issue 3.4.

Cited by

  1. Design and Implementation of Crowd-sourced Q&A System Based on Social Chat-bot vol.15, pp.11, 2017, https://doi.org/10.14801/jkiit.2017.15.11.125