Dialogue Organization in Polint-112-SMS

  • Justyna Walkowska
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6562)

Abstract

This paper describes the organization of dialogue in the Polint-112-SMS system, a multi-user knowledge-management system with natural language interface. It presents the main goals of the system’s dialoguing strategy and the most important dialogue-oriented algorithms of different modules of the system. The algorithms allow for efficient handling of: questions asked by the system to obtain missing information, the need to pair different types of answers and questions in the asynchronous mode of communication, different semantic interpretations proposed by the parser, the occurrence of anaphora, and a few more.

Keywords

human-machine dialogue dialogue model SMS corpus knowledge management system 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dunin-Keplicz, B.: Towards better understanding of anaphora. In: Proceedings of 1st Conference of the European Chapter of ACL, E-ACL 1983, Pisa, pp. 139–143 (1983)Google Scholar
  2. 2.
    Fairon, C., Paumier, S.: A translated corpus of 30,000 French SMS. In: Proceedings of LREC 2006, Genova (2006)Google Scholar
  3. 3.
    Fellbaum, C.D.: WordNet: An Electronic Lexical Database. MIT Press, Cambridge (1998)MATHGoogle Scholar
  4. 4.
    Fillmore, C.J.: Frame semantics. In: Linguistics in the Morning Calm, pp. 111–137. Hanshin Publishing Co., Seoul (1982)Google Scholar
  5. 5.
    Milward, D., Beveridge, M.: Ontology-based dialogue systems. In: 3rd Workshop on Knowledge and Reasoning in Practical Dialogue Systems (IJCAI 2003), pp. 9–18. MIT Press, Cambridge (2003)Google Scholar
  6. 6.
    Minker, W., Bennacef, S.: Speech and Human-Machine Dialogue. The Kluwer International Series in Engineering and Computer Science. Kluwer Academic Publishers, Massachusetts (2004)Google Scholar
  7. 7.
    Vetulani, Z.: Question answering system for Polish (POLINT) and its language resources. In: Proceedings of the Question Answering - Strategy and Resources Workshop, LREC 2002, Las Palmas de Gran Canaria (2002)Google Scholar
  8. 8.
    Vetulani, Z., Dąbrowski, A., Obrębski, T., Osiński, J., Kubacki, P., Kubis, M., Marciniak, J., Vetulani, G., Walkowska, J., Witalewski, K.: Zasoby językowe i technologie przetwarzania tekstu. POLINT-112-SMS jako przykład aplikacji z zakresu bezpieczeñstwa publicznego, Wydawnictwo Naukowe Uniwersytetu im. Adama Mickiewicza w Poznaniu (2010)Google Scholar
  9. 9.
    Vetulani, Z., Marciniak, J.: Corpus based methodology in the study and design of systems with emulated linguistic competence. In: Christodoulakis, D.N. (ed.) NLP 2000. LNCS (LNAI), vol. 1835, pp. 346–357. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  10. 10.
    Vetulani, Z., Marciniak, J., Konieczka, P., Walkowska, J.: An SMS-based system architecture (logical model) to support management of information exchange in emergency situations. POLINT-112-SMS project. In: Intelligent Information Processing IV, 5th IFIP International Conference on Intelligent Information Processing, Beijing, China, October 19-22, pp. 240–253. Springer, Boston (2008)Google Scholar
  11. 11.
    Vetulani, Z., Walkowska, J., Obrębski, T., Konieczka, P., Rzepecki, P., Marciniak, J.: PolNet - Polish WordNet project algorithm. In: Vetulani, Z., Uszkoreit, H. (eds.) LTC 2007. LNCS, vol. 5603, pp. 369–381. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  12. 12.
    Walkowska, J.: Gathering and Analysis of a Corpus of Polish SMS Dialogues. In: Challenging Problems of Science. Computer Science. Recent Advances in Intelligent Information Systems, pp. 145–157. Academic Publishing House EXIT, Warsaw (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Justyna Walkowska
    • 1
  1. 1.Department of Computer Linguistics and Artificial Intelligence Faculty of Mathematics and Computer ScienceAdam Mickiewicz UniversityPoznańPoland

Personalised recommendations