Answering Contextual Questions Based on the Cohesion with Knowledge

  • Tatsunori Mori
  • Shinpei Kawaguchi
  • Madoka Ishioroshi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4285)


In this paper, we propose a Japanese question-answering (QA) system to answer contextual questions using a Japanese non-contextual QA system. The contextual questions usually contain reference expressions to refer to previous questions and their answers. We address the reference resolution in contextual questions by finding the interpretation of references so as to maximize the cohesion with knowledge. We utilize the appropriateness of the answer candidate obtained from the non-contextual QA system as the degree of the cohesion. The experimental results show that the proposed method is effective to disambiguate the interpretation of contextual questions.


Semantic Category Case Element Topic Shift Current Question Gathering Type 
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.
    Walker, M., Iida, M., Cote, S.: Japanese discourse and the process of centering. Computational Linguistics 20(2), 193–232 (1994)Google Scholar
  2. 2.
    Voorhees, E.M.: Overview of the TREC 2001 question answering track. In: Proceedings of the tenth Text Retrieval Conferene (TREC 2001) (2001)Google Scholar
  3. 3.
    Kato, T., Fukumoto, J., Masui, F., Kando, N.: Are open-domain question answering technologies useful for information access dialogues? ACM Transactions on Asian Language Information Processing (TALIP) 4(3), 243–262 (2005)CrossRefGoogle Scholar
  4. 4.
    Murata, Y., Akiba, T., Fujii, A., Itou, K.: Question answering experiments at NTCIR-5: Acquisition of answer evaluation patterns and context processing using passage retrieval. In: Proceedings of the Fifth NTCIR Workshop Meeting (2005)Google Scholar
  5. 5.
    Matsuda, M., Fukumoto, J.: Answering questions of IAD task using reference resolution of follow-up questions. In: Proceedings of the Fifth NTCIR Workshop Meeting (2005)Google Scholar
  6. 6.
    Nariyama, S.: Grammar for ellipsis resolution in Japanese. In: Proceedings of the 9th International Conference on Theoretical and Methodological Issues in Machine Translation, pp. 135–145 (2002)Google Scholar
  7. 7.
    Mori, T.: Japanese question-answering system using A* search and its improvement. ACM Transactions on Asian Language Information Processing (TALIP) 4(3), 280–304 (2005)CrossRefGoogle Scholar
  8. 8.
    Ishioroshi, M., Mori, T.: A method of list-type question-answering based on the distribution of answer score generated by a ranking-type Q/A system. SIG Technical Reports 2005-NL-169, Information Processing Society of Japan (2005) (in Japanese)Google Scholar
  9. 9.
    Yamura-Takei, M.: Approaches to zero adnominal recognition. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL 2003) Student Research Workshop, ACL, pp. 87–94 (2003)Google Scholar
  10. 10.
    Kawahara, D., Kurohashi, S.: Zero pronoun resolution based on automatically constructed case frames and structural preference of antecedents. In: Su, K.-Y., Tsujii, J., Lee, J.-H., Kwong, O.Y. (eds.) IJCNLP 2004. LNCS, vol. 3248, pp. 334–341. Springer, Heidelberg (2005)Google Scholar
  11. 11.
    Kato, T., Fukumoto, J., Masui, F.: An Overview of NTCIR-5 QAC3. In: Proceedings of the Fifth NTCIR Workshop Meeting (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tatsunori Mori
    • 1
  • Shinpei Kawaguchi
    • 1
  • Madoka Ishioroshi
    • 1
  1. 1.Graduate School of Environment and Information SciencesYokohama National UniversityHodogaya, YokohamaJapan

Personalised recommendations