Analyzing Interactive QA Dialogues Using Logistic Regression Models

  • Manuel Kirschner
  • Raffaella Bernardi
  • Marco Baroni
  • Le Thanh Dinh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5883)


With traditional Question Answering (QA) systems having reached nearly satisfactory performance, an emerging challenge is the development of successful Interactive Question Answering (IQA) systems. Important IQA subtasks are the identification of a dialogue-dependent typology of Follow Up Questions (FU Qs), automatic detection of the identified types, and the development of different context fusion strategies for each type. In this paper, we show how a system relying on shallow cues to similarity between utterances in a narrow dialogue context and other simple information sources, embedded in a machine learning framework, can improve FU Q answering performance by implicitly detecting different FU Q types and learning different context fusion strategies to help re-ranking their candidate answers.


Context Feature Question Answering Context Type Pointwise Mutual Information Topic Shift 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yang, F., Feng, J., Di Fabbrizio, G.: A data driven approach to relevancy recognition for contextual question answering. In: Interactive Question Answering Workshop (2006)Google Scholar
  2. 2.
    Bertomeu, N.: A Memory and Attention-Bases Approach to Fragment Resolution and its Application in a Question Answering System. PhD thesis, Universität des Saarlandes (2007)Google Scholar
  3. 3.
    Van Schooten, B., Op den Akker, R., Rosset, S., Galibert, O., Max, A., Illouz, G.: Follow-up question handling in the imix and ritel systems: A comparative study. Nat. Lang. Eng. 15(1), 97–118 (2009)CrossRefGoogle Scholar
  4. 4.
    Chai, J.Y., Jin, R.: Discourse structure for context question answering. In: Proceedings of the Workshop on Pragmatics of Question Answering at HLT-NAACL 2004 (2004)Google Scholar
  5. 5.
    Sun, M., Chai, J.: Discourse processing for context question answering based on linguistic knowledge. Know.-Based Syst. 20(6), 511–526 (2007)CrossRefGoogle Scholar
  6. 6.
    Burek, G., De Roeck, A., Zdrahal, Z.: Hybrid mappings of complex questions over an integrated semantic space. In: Andersen, K.V., Debenham, J., Wagner, R. (eds.) DEXA 2005. LNCS, vol. 3588. Springer, Heidelberg (2005)Google Scholar
  7. 7.
    Tomás, D., Vicedo, J., Bisbal, E., Moreno, L.: Experiments with lsa for passage re-ranking in question answering. In: CLEF Proceedings (2006)Google Scholar
  8. 8.
    Moschitti, A., Quarteroni, S.: Kernels on linguistic structures for answer extraction. In: Proceedings of ACL 2008: HLT, Short Papers, pp. 113–116 (2008)Google Scholar
  9. 9.
    Kirschner, M., Bernardi, R.: An empirical view on iqa follow-up questions. In: Proc. of the 8th SIGdial Workshop on Discourse and Dialogue (2007)Google Scholar
  10. 10.
    Manning, C.D., Schütze, H.: Foundations of statistical natural language processing. MIT Press, Cambridge (1999)zbMATHGoogle Scholar
  11. 11.
    Sahlgren, M.: The Word-Space Model. Dissertation, Stockholm University (2006)Google Scholar
  12. 12.
    Mihalcea, R., Corley, C., Strapparava, C.: Corpus-based and knowledge-based measures of text semantic similarity. In: Proceedings of AAAI (2006)Google Scholar
  13. 13.
    Fellbaum, C. (ed.): WordNet: An electronic lexical database. MIT Press, Cambrdige (1998)zbMATHGoogle Scholar
  14. 14.
    Agresti, A.: Categorical data analysis. Wiley, New York (2002)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Manuel Kirschner
    • 1
  • Raffaella Bernardi
    • 1
  • Marco Baroni
    • 2
  • Le Thanh Dinh
    • 1
    • 3
  1. 1.KRDB, Faculty of Computer ScienceFree University of Bozen-BolzanoItaly
  2. 2.Center for Mind/Brain SciencesUniversity of TrentoItaly
  3. 3.Institute of Formal and Applied Linguistics, Faculty of Mathematics and PhysicsCharles University in PragueCzech Republic

Personalised recommendations