Hierarchical Answer Selection Framework for Multi-passage Machine Reading Comprehension

  • Zhaohui Li
  • Jun Xu
  • YanYan Lan
  • Jiafeng Guo
  • Yue Feng
  • Xueqi Cheng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11168)


Machine reading comprehension (MRC) on real web data, which means finding answers from a set of candidate passages for a question, is a quite arduous task in natural language processing. Most state-of-the-art approaches select answers from all passages or from only one single golden paragraph, which may cause the overlapping information and the lack of key information. To address these problems, this paper proposes a hierarchical answer selection framework that can select main content from a set of passages based on the question, and predict final answer within this main content. Specifically, three main parts are employed in this pipeline: First, the passage selection model uses a classification mechanism to select passages by passages content and title information which is not fully used in other models; Second, a key sentences sequence selection mechanism is modeled by Markov-Decision-Process (MDP) in order to gain as much as effectual answer information as possible; Finally, a match-LSTM model is employed to extract the final answer from the selected main content. These three modules that shared the same attention-based semantic network and we conduct experimental on DuReader search dataset. The results show that our framework outperforms the baseline by a large margin.


Machine reading comprehension Markov Decision Process Reinforcement learning Natural language process 


  1. 1.
    He, W., et al.: DuReader: a Chinese machine reading comprehension dataset from real-world applications. arXiv preprint arXiv:1711.05073 (2017)
  2. 2.
    Hermann, K.M., et al.: Teaching machines to read and comprehend. In: Advances in Neural Information Processing Systems, pp. 1693–1701 (2015)Google Scholar
  3. 3.
    Hill, F., Bordes, A., Chopra, S., Weston, J.: The goldilocks principle: reading children’s books with explicit memory representations. arXiv preprint arXiv:1511.02301 (2015)
  4. 4.
    Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: Race: large-scale reading comprehension dataset from examinations. arXiv preprint arXiv:1704.04683 (2017)
  5. 5.
    Nguyen, T., et al.: MS MARCO: a human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)
  6. 6.
    Pan, B., Li, H., Zhao, Z., Cao, B., Cai, D., He, X.: MEMEN: multi-layer embedding with memory networks for machine comprehension. arXiv preprint arXiv:1707.09098 (2017)
  7. 7.
    Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)zbMATHGoogle Scholar
  8. 8.
    Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAd: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
  9. 9.
    Seo, M., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603 (2016)
  10. 10.
    Shen, Y., Huang, P.S., Gao, J., Chen, W.: ReasoNet: learning to stop reading in machine comprehension. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1047–1055. ACM (2017)Google Scholar
  11. 11.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT Press, Cambridge (1998)Google Scholar
  12. 12.
    Tan, C., Wei, F., Yang, N., Lv, W., Zhou, M.: S-Net: from answer extraction to answer generation for machine reading comprehension. arXiv preprint arXiv:1706.04815 (2017)
  13. 13.
    Wang, S., Jiang, J.: Machine comprehension using match-LSTM and answer pointer. arXiv preprint arXiv:1608.07905 (2016)
  14. 14.
    Wang, S., et al.: Reinforced reader-ranker for open-domain question answering. arXiv preprint arXiv:1709.00023 (2017)
  15. 15.
    Wang, S., et al.: Evidence aggregation for answer re-ranking in open-domain question answering. arXiv preprint arXiv:1711.05116 (2017)
  16. 16.
    Wang, Y., et al.: Multi-passage machine reading comprehension with cross-passage answer verification. arXiv preprint arXiv:1805.02220 (2018)
  17. 17.
    Xiong, C., Zhong, V., Socher, R.: Dynamic coattention networks for question answering. arXiv preprint arXiv:1611.01604 (2016)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Zhaohui Li
    • 1
  • Jun Xu
    • 1
  • YanYan Lan
    • 1
  • Jiafeng Guo
    • 1
  • Yue Feng
    • 1
  • Xueqi Cheng
    • 1
  1. 1.CAS Key Lab of Network Data Science and Technology, Institute of Computing TechnologyChinese Academy of SciencesBeijingChina

Personalised recommendations