Proceedings

Interfacing Virtual Agents with Collaborative Knowledge: Open Domain Question Answering Using Wikipedia-Based Topic Models

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 1896-1901.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-317

© 2011 International Joint Conferences on Artificial Intelligence

Abstract

This paper is concerned with the use of conversational agents as an interaction paradigm for accessing open domain encyclopedic knowledge by means of Wikipedia. More precisely, we describe a dialogue-based question answering system for German which utilizes Wikipedia-based topic models as a reference point for context detection and answer prediction. We investigate two different per- spectives to the task of interfacing virtual agents with collaborative knowledge. First, we exploit the use of Wikipedia categories as a basis for identifying the broader topic of a spoken utterance. Second, we describe how to enhance the conversational behavior of the virtual agent by means of a Wikipedia-based question answering component which incorporates the question topic. At large, our approach identifies topic-related focus terms of a user’s question, which are subsequently mapped onto a category taxonomy. Thus, we utilize the taxonomy as a reference point to derive topic labels for a user’s question. The employed topic model is thereby based on explicitly given concepts as represented by the document and category structure of the Wikipedia knowledge base. Identified topic categories are subsequently combined with different linguistic filtering methods to improve answer candidate retrieval and reranking. Results show that the topic model approach contributes to an enhancement of the conversational behavior of virtual agents.

  1. [Adafre and van Genabith, 2009] Sisay Fissaha Adafre and Josef van Genabith. A hybrid filtering approach for ques- tion answering. In Proceedings of the 14th International Lexical Functional Grammar Conference (LFG-09), Cam- bridge, UK, 2009.
  2. [Ahn et al., 2004] David Ahn, Valentin Jijkoun, Gilad Mishne, Karin Mller, Maarten de Rijke, and Stefan Schlobach. Using wikipedia at the trec qa track. In Pro- ceedings of TREC 2004, 2004.
  3. [Bizer et al., 2009] Christian Bizer, Jens Lehmann, Georgi Kobilarov, Sören Auer, Christian Becker, Richard Cyga- niak, and Sebastian Hellmann. Dbpedia -a crystalliza- tion point for the web of data. Web Semant., 7:154-165, September 2009.
  4. [Breuing, 2010] Alexa Breuing. Improving human-agent conversations by accessing contextual knowledge from wikipedia. In Proceedings of the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelli- gent Agent Technology -Volume 03, WI-IAT '10, pages 428-431, Washington, DC, USA, 2010. IEEE Computer Society.
  5. [Buscaldi and Rosso, 2006] David Buscaldi and Paolo Rosso. Mining Knowledge from Wikipedia from the question answering task. In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC 2006), Genoa, Italy, 2006.
  6. [Cimiano and Kopp, 2010] P. Cimiano and S. Kopp. Access- ing the web of data through embodied virtual characters. Semantic Web Journal, 2010.
  7. [Cramer et al., 2006] Irene Cramer, Jochen L. Leidner, and Dietrich Klakow. Building an evaluation corpus for ger- man question answering by harvesting wikipedia, 2006.
  8. [Cunningham et al., 2002] H. Cunningham, D. Maynard, K. Bontcheva, and V. Tablan. GATE: A framework and graphical development environment for robust NLP tools and applications. In Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics, 2002.
  9. [Fissaha Adafre et al., 2007] Sisay Fissaha Adafre, Valentin Jijkoun, and Maarten de Rijke. Fact discovery in wikipedia. In Proceedings of the IEEE/WIC/ACM Inter- national Conference on Web Intelligence, WI '07, pages 177-183, Washington, DC, USA, 2007. IEEE Computer Society.
  10. [Furbach et al., 2008] Ulrich Furbach, Ingo Glöckner, Her- mann Helbig, and Björn Pelzer. Loganswer -a deduction- based question answering system (system description). In Proceedings of the 4th international joint conference on Automated Reasoning, IJCAR '08, pages 139-146, Berlin, Heidelberg, 2008. Springer-Verlag.
  11. [Gabrilovich and Markovitch, 2007] Evgeniy Gabrilovich and Shaul Markovitch. Computing Semantic Relatedness using Wikipedia-based Explicit Semantic Analysis. Proceedings of the 20th International Joint Conference on Artificial Intelligence, pages 6-12, 2007. IJCAI
  12. [Giampiccolo et al., 2007] Danilo Giampiccolo, Pamela Forner, Jesús Herrera, Anselmo Peñas, Christelle Ay- ache, Corina Forascu, Valentin Jijkoun, Petya Osenova, Paulo Rocha, Bogdan Sacaleanu, and Richard F. E. Sutcliffe. Overview of the clef 2007 multilingual question answering track. In CLEF, pages 200-236, 2007.
  13. [Hatcher et al., 2010] Erik Hatcher, Otis Gospodnetic, and Mike McCandless. Lucene in Action. Manning, 2nd re- vised edition. edition, 2010.
  14. [Kaisser, 2008] Michael Kaisser. The qualim question an- swering demo: supplementing answers with paragraphs drawn from wikipedia. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Demo Session, HLT- Demonstrations '08, pages 32-35, Morristown, NJ, USA, 2008. Association for Computational Linguistics.
  15. [Katz et al., 2002] Boris Katz, Sue Felshin, Deniz Yuret, Ali Ibrahim, Jimmy J. Lin, Gregory Marton, Alton Jerome McFarland, and Baris Temelkuran. Omnibase: Uniform access to heterogeneous data for question answering. In Natural Language Processing and Information Systems, 6th International Conference on Applications of Natural Language to Information Systems, NLDB 2002, Stock- holm, Sweden, June 27-28, 2002, Revised Papers, volume 2553 of Lecture Notes in Computer Science, pages 230- 234. Springer, 2002.
  16. [Koehler et al., 2008] Florian Koehler, Hinrich Schütze, and Michaela Atterer. A question answering system for ger- man. experiments with morphological linguistic resources. In Proceedings of the International Conference on Lan- guage Resources and Evaluation, LREC 2008, 26 May -1 June 2008, Marrakech, Morocco, 2008.
  17. [Kopp et al., 2005] S. Kopp, L. Gesellensetter, N. Krämer, and I. Wachsmuth. A conversational agent as museum guide -design and evaluation of a real-world application. In Panayiotopoulos and others (Eds.), editors, Intelligent Virtual Agents, LNAI 3661, pages 329-343, Berlin, 2005. Springer.
  18. [Lagus and Kuusisto, 2002] Krista Lagus and Jukka Kuu- sisto. Topic identification in natural language dialogues using neural networks. In Proceedings of the 3rd SIGdial workshop on Discourse and dialogue -Volume 2, SIG- DIAL '02, pages 95-102, Stroudsburg, PA, USA, 2002. Association for Computational Linguistics.
  19. [Lopez et al., 2010] Vanessa Lopez, Andriy Nikolov, Marta Sabou, Victoria S. Uren, Enrico Motta, and Mathieu d'Aquin. Scaling up question-answering to linked data. In Proceedings of the EKAW -Knowledge Engineering and Management by the Masses -17th International Con- ference, EKAW 2010, Lisbon, Portugal, October 11-15, 2010., pages 193-210, 2010.
  20. [Neumann and Sacaleanu, 2004] Günter Neumann and Bog- dan Sacaleanu. A Cross Language Question Answering System for German and English. In Carol Peters, Julio Gonzalo, Martin Braschler, and Michael Kluck, editors, Comparative Evaluation of Multilingual Information Ac- cess Systems, volume 3237 of Lecture Notes in Computer Science, pages 101-109. Springer Berlin / Heidelberg, 2004.
  21. [Schank, 1977] Roger C. Schank. Rules and topics in con- versation. Cognitive Science, 1(4):421-441, 1977.
  22. [Schmid, 1994] Helmut Schmid. Probabilistic part-of- speech tagging using decision trees. In Proceedings of the International Conference on New Methods in Language Processing, Manchester, UK, 1994.
  23. [Schönhofen, 2009] Peter Schönhofen. Identifying docu- ment topics using the wikipedia category network. Web Intelli. and Agent Sys., 7:195-207, April 2009.
  24. [Sonntag, 2009] Daniel Sonntag. Introspection and adapt- able model integration for dialogue-based question an- swering. In Proceedings of the 21st international jont conference on Artifical intelligence, pages 1549-1554, San Francisco, CA, USA, 2009. IJCAI
  25. [Tunstall-Pedoe, 2010] William Tunstall-Pedoe. True knowledge: Open-domain question answering using structured knowledge and inference. AI Magazine, 31(3):80-92, 2010.
  26. [Waltinger and Mehler, 2009] Ulli Waltinger and Alexander Mehler. Social semantics and its evaluation by means of semantic relatedness and open topic models. In Proceed- ings of the 2009 IEEE/WIC/ACM International Joint Con- ference on Web Intelligence and Intelligent Agent Technol- ogy -Volume 01, WI-IAT '09, pages 42-49, Washington, DC, USA, 2009. IEEE Computer Society.
  27. [Zheng, 2002] Zhiping Zheng. Answerbus question answer- ing system. In Proceedings of the second international conference on Human Language Technology Research, HLT '02, pages 399-404, San Francisco, CA, USA, 2002.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards