FAQ answering on WWW using shallow language understanding

  • E. Sneiders
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT)


While advertising some product, service or activity, information providers often put forward so called frequently asked questions (FAQ). The answers to these questions help people to understand details of the information. The research presented in this paper will help to improve users’ interaction with information supplied through an FAQ collection on the World Wide Web. Problems with existing FAQ lists are observed and solutions to these problems proposed.

In this paper, the development of an automated Web-based FAQ answering system, which provides pre-stored answers to users’ questions asked in natural English, is discussed. The natural language interface makes users’ interaction with the system more enjoyable, as well as lets the FAQ authors find out what questions the users actually have. The system maintains its own question-and-answer base. The structure of the database, which is implemented as a relational database, as well as the searching algorithms, are discussed. The system uses shallow language understanding to process questions. Within the scope of this research, the Prioritized Keyword Matching algorithm, which is based on distinguishing primary and secondary keywords, has been developed. It is used to match the user’s question against separate entries in a narrow subset of the question-and-answer base.


FAQ frequently asked questions FAQ answering question answering WWW shallow language understanding keyword matching 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bubenko, J. jr (1994) Enterprise Modelling. Ingènierie de Systemes d’Information, Vol.2, issue 6, p.657–678Google Scholar
  2. Burg, J.F.M. (1997) Linguistic Instruments in Requirements Engineering. IOS Press, NetherlandsGoogle Scholar
  3. Burke, R., Hammond, K., Kulyukin, V., Lytinen, S., Tomuro, N. and Schoenberg, S. (1997) Question Answering from Frequently Asked Question Files — Experiences with the FAQ Finder System. AI Magazine, Vol.18, no.2, p.57–66Google Scholar
  4. Delphi url (1997) Delphi Technical Information Documents. (valid in April, 1998)
  5. EKD manual (1998) EKD User Guide. Internal document at DSV, Stockholm University/Royal Institute of Technology, SwedenGoogle Scholar
  6. EKD url (1997) EKD — Enterprise Knowledge Development, (valid in April, 1998)Google Scholar
  7. Hammond, K., Burke, R., Martin, C. and Lytinen, S. (1995) FAQ Finder: a Case-Based Approach to Knowledge Navigation. Proceedings. The 11th Conference on Artificial Intelligence for Applications, IEEE Comput. Soc. Press, Los Alamitos, CA, USA, pp.80–86CrossRefGoogle Scholar
  8. Salton, G. (1989) Automatic Text Processing. The Transformation, Analysis, and Retrieval of Information by Computer. Addison-Wesley Publishing CompanyGoogle Scholar
  9. Spink, A. (1997, August) Information Science: A Third Feedback Framework. Journal of the American Society for Information Science, pp.728–740Google Scholar
  10. Whitehead, S.D. (1995, December) Auto-FAQ: an Experiment in Cyberspace Leveraging. Computer Networks and ISDN Systems, Vol.28, no. 1–2, pp. 137–146CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 1998

Authors and Affiliations

  • E. Sneiders
    • 1
  1. 1.Department of Computer and System SciencesRoyal Institute of Technology and Stockholm UniversityKistaSweden

Personalised recommendations