Advertisement

Towards Answering Geography Questions in Gaokao: A Hybrid Approach

  • Zhiwei Zhang
  • Lingling Zhang
  • Hao Zhang
  • Weizhuo He
  • Zequn Sun
  • Gong Cheng
  • Qizhi Liu
  • Xinyu Dai
  • Yuzhong Qu
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 957)

Abstract

Answering geography questions in a university’s entrance exam (e.g., Gaokao in China) is a new AI challenge. In this paper, we analyze its difficulties in problem understanding and solving, which suggest the necessity of developing novel methods. We present a pipeline approach that mixes information retrieval techniques with knowledge engineering and exhibits an interpretable problem solving process. Our implementation integrates question parsing, semantic matching, and spreading activation over a knowledge graph to generate answers. We report its promising performance on a representative sample of 1,863 questions used in real exams. Our analysis of failures reveals a number of open problems to be addressed in the future.

Keywords

Information retrieval Knowledge engineering Natural language processing Question answering 

Notes

Acknowledgements

This work was supported in part by the NSFC under Grants 61772264 and 61572247, in part by the 863 Program under Grant 2015AA015406, and in part by the Qing Lan and Six Talent Peaks Programs of Jiangsu Province.

References

  1. 1.
    Angele, J., Moench, E., Oppermann, H., Staab, S., Wenke, D.: Ontology-based query and answering in chemistry: OntoNova project Halo. In: Fensel, D., Sycara, K., Mylopoulos, J. (eds.) ISWC 2003. LNCS, vol. 2870, pp. 913–928. Springer, Heidelberg (2003).  https://doi.org/10.1007/978-3-540-39718-2_58CrossRefGoogle Scholar
  2. 2.
    Cheng, G., Zhu, W., Wang, Z., Chen, J., Qu, Y.: Taking up the Gaokao challenge: an information retrieval approach. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp. 2479–2485. International Joint Conferences on Artificial Intelligence, New York, July 2016Google Scholar
  3. 3.
    Clark, P., Etzioni, O., Khot, T., Sabharwal, A., Tafjord, O., Turney, P.: Combining retrieval, statistics, and inference to answer elementary science questions. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 2580–2586. AAAI Press, Phoenix, February 2016Google Scholar
  4. 4.
    Ferrucci, D., et al.: Building Watson: an overview of the DeepQA project. AI Mag. 31(3), 59–79 (2010)CrossRefGoogle Scholar
  5. 5.
    Fujita, A., Kameda, A., Kawazoe, A., Miyao, Y.: Overview of Todai robot project and evaluation framework of its NLP-based problem solving. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation, pp. 2590–2597. European Language Resources Association, Reykjavik, May 2014Google Scholar
  6. 6.
    Gunning, D., et al.: Project Halo update - progress toward digital aristotle. AI Mag. 31(3), 33–58 (2010)CrossRefGoogle Scholar
  7. 7.
    Hidey, C., McKeown, K.: Identifying causal relations using parallel Wikipedia articles. In: Proceedings of the Fifty-Fourth Annual Meeting of the Association for Computational Linguistics, pp. 1424–1433. Association for Computational Linguistics, Berlin, August 2016Google Scholar
  8. 8.
    Hosseini, M.J., Hajishirzi, H., Etzioni, O., Kushman, N.: Learning to solve arithmetic word problems with verb categorization. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 523–533. Association for Computational Linguistics, Doha, October 2014Google Scholar
  9. 9.
    Kolomiyets, O., Moens, M.F.: A survey on question answering technology from an information retrieval perspective. Inf. Sci. 181(24), 5412–5434 (2011)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Liang, P.: Learning executable semantic parsers for natural language understanding. Commun. ACM 49(9), 68–76 (2016)CrossRefGoogle Scholar
  11. 11.
    Shi, S., Wang, Y., Lin, C.Y., Liu, X., Rui, Y.: Automatically solving number word problems by semantic parsing and reasoning. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1132–1142. Association for Computational Linguistics, Lisbon, September 2015Google Scholar
  12. 12.
    Tan, M., dos Santos, C., Xiang, B., Zhou, B.: Improved representation learning for question answer matching. In: Proceedings of the Fifty-Fourth Annual Meeting of the Association for Computational Linguistics, pp. 464–473. Association for Computational Linguistics, Berlin, August 2016Google Scholar
  13. 13.
    Tong, H., Faloutsos, C.: Center-piece subgraphs: problem definition and fast solutions. In: Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 404–413. Association for Computing Machinery, Philadelphia, August 2006Google Scholar
  14. 14.
    Yu, K., Liu, Q., Zheng, Y., Zhao, T., Zheng, D.: History question classification and representation for Chinese Gaokao. In: Proceedings of the Twentieth International Conference on Asian Language Processing, pp. 129–132. Institute of Electrical and Electronics Engineers, Tainan, November 2016Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Zhiwei Zhang
    • 1
  • Lingling Zhang
    • 1
  • Hao Zhang
    • 1
  • Weizhuo He
    • 1
  • Zequn Sun
    • 1
  • Gong Cheng
    • 1
  • Qizhi Liu
    • 1
  • Xinyu Dai
    • 1
  • Yuzhong Qu
    • 1
  1. 1.National Key Laboratory for Novel Software TechnologyNanjing UniversityNanjingChina

Personalised recommendations