Advertisement

Chinese Question-Answering: Comparing Monolingual with English-Chinese Cross-Lingual Results

  • Kui-Lam Kwok
  • Peter Deng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4182)

Abstract

A minimal approach to Chinese factoid QA is described. It employs entity extraction software, template matching, and statistical candidate answer ranking via five evidence types, and does not use explicit word segmentation or Chinese syntactic analysis. This simple approach is more portable to other Asian languages, and may serve as a base on which more precise techniques can be used to improve results. Applying to the NTCIR-5 monolingual environment, it delivers medium top-1 accuracy and MRR of .295, .3381 (supported answers) and .41, .4998 (including unsupported) respectively. When applied to English-Chinese cross language QA with three different forms of English-Chinese question translation, it attains top-1 accuracy and MRR of .155, .2094 (supported) and .215, .2932 (unsupported), about ~52% to ~62% of monolingual effectiveness. CLQA improvements via successively different forms of question translation are also demonstrated.

Keywords

Question Answering Question Classification Answer Candidate Score Versus Multiple Translation 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Voorhees, E.M., Tice, D.M.: The TREC-8 Question Answering Track Evaluation. In: Information Technology: The Eighth Text REtrieval Conference (TREC-8), pp. 83–105. NIST Special Publication 500-246 (2000)Google Scholar
  2. 2.
    Ramakrishnan, G., Chakrabarti, S., Paranjpe, D., Bhattacharyya, P.: Is Question Answering an Acquired Skill? In: Proc. of 13th International WWW Conference, pp. 111–120 (2004)Google Scholar
  3. 3.
    Magnini, B., Romagnoli, S., Vallin, A., Herrera, J., Peñas, A., Peinado, V., Verdejo, F., de Rijke, M.: The Multiple Language Question Answering Track at CLEF 2003. In: Peters, C., Gonzalo, J., Braschler, M., Kluck, M. (eds.) CLEF 2003. LNCS, vol. 3237, pp. 471–486. Springer, Heidelberg (2004); http://clef.iei.pi.cnr.it/ CrossRefGoogle Scholar
  4. 4.
    Sekine, S., Grishman, R.: Hindi-English Cross-lingual Question-Answering System. ACM TALIP 2, 181–192 (2004)CrossRefGoogle Scholar
  5. 5.
    Sasaki, Y., Chen, H.-H., Chen, K.-H., Lin, C.-J.: Overview of the NTCIR-5 Cross-lingual Question Answering Task. In: Proc. Fifth Workshop Meeting on Evaluation of Information Access Technologies: IR, QA and CLIR, NII, Tokyo, pp. 175–185 (2005)Google Scholar
  6. 6.
    Kwok, K.L.: Improving English & Chinese Ad-Hoc Retrieval: A Tipster Text Phase 3 Project Report. Information Retrieval 3, 313–338 (2000)MATHCrossRefGoogle Scholar
  7. 7.
    Chang, Y., Xu, H., Bai, S.: A Re-examination of IR Techniques in QA Systems. In: Su, K.-Y., Tsujii, J., Lee, J.-H., Kwong, O.Y. (eds.) IJCNLP 2004. LNCS (LNAI), vol. 3248, pp. 71–80. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Plamondon, L., Foster, G.: Quantum, a French/English Cross-Language Question Answering System. In: Peters, C., Gonzalo, J., Braschler, M., Kluck, M. (eds.) CLEF 2003. LNCS, vol. 3237, pp. 549–558. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Bikel, D.M., Miller, S., Schwartz, R., Weischedel, R.: A High-Performance Learning Name-Finder. In: Proc. Conference of Applied Natural Language Processing (1997)Google Scholar
  10. 10.
    Lee, C.-W., Shih, C.-W., Day, M.-Y., Tsai, T.-H., Jiang, T.-J., Wu, C.-W., Sung, C.-L., Chen, Y.-R., Wu, S.-H., Hsu, W.-L.: ASQA: Academia Sinica Question Answering System for NTCIR- 5 CLQA. In: Proc. Fifth Workshop Meeting on Evaluation of Information Access Technologies: IR, QA and CLIR, NII, Tokyo, pp. 202–208 (2005)Google Scholar
  11. 11.
    Lin, F., Shima, H., Wang, M., Mitamura, T.: CMU JAVELIN System for NTCIR5 CLQA1. In: Proc. Fifth Workshop Meeting on Evaluation of Information Access Technologies: IR, QA and CLIR, NII, Tokyo, pp. 194–201 (2005)Google Scholar
  12. 12.
    Kwok, K.L., Deng, P., Sun, H.L., Xu, W., Dinstl, N., Peng, P., Doyon, J.: CHINET – a Chinese Name Finder for Docucment Triage. In: Proc. 2005 Intl. Conf. on Intelligence Analysis (2005); Sasaki, Y, Chen, H-H, Chen, K-H, Lin, C-J.: Overview of the NTCIR-5 Cross-lingual Question Answering Task. In: Proc. Fifth Workshop Meeting on Evaluation of Information Access (2005), https://analysis.mitre.org/proceedings_agenda.htm#papers
  13. 13.
    Kwok, K.L., Grunfeld, L., Sun, H.L., Deng, P.: TREC2004 Robust Track Experiments using PIRCS. In: Information Technology: The Fourteen Text REtrieval Conference (TREC- 2004). NIST Special Publication 500-261 (2005)Google Scholar
  14. 14.
    Brill, E., Lin, J., Banko, M., Dumais, S., Ng, A.: Data-Intensive Question Answering. In: Information Technology: The Tenth Text REtrieval Conference, TREC 2001, pp. 393–400. NIST Special Publication 500-250 (2002)Google Scholar
  15. 15.
    Kwok, K.L., Deng, P., Dinstl, N., Choi, S.: NTCIR-5 English-Chinese Cross Language Question-Answering Experiments using PIRCS. In: Proc. Fifth Workshop Meeting on Evaluation of Information Access Technologies: IR, QA and CLIR, NII, Tokyo, pp. 209–214 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kui-Lam Kwok
    • 1
  • Peter Deng
    • 1
  1. 1.Computer Science Department, Queens CollegeCity University of New YorkNew YorkU.S.A.

Personalised recommendations