A Chinese Question Answering System for Single-Relation Factoid Questions

  • Yuxuan LaiEmail author
  • Yanyan Jia
  • Yang Lin
  • Yansong Feng
  • Dongyan Zhao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10619)


Aiming at the task of open domain question answering based on knowledge base in NLPCC 2017, we build a question answering system which can automatically find the promised entities and predicates for single-relation questions. After a features based entity linking component and a word vector based candidate predicates generation component, deep convolutional neural networks are used to rerank the entity-predicate pairs, and all intermediary scores are used to choose the final predicted answers. Our approach achieved the F1-score of 47.23% on test data which obtained the first place in the contest of NLPCC 2017 Shared Task 5 (KBQA sub-task). Furthermore, there are also a series of experiments which can help other developers understand the contribution of every part of our system.


Natural language question answering Knowledge base Information extraction Deep convolutional neural network 



We would like to thank members in our NLP group and the anonymous reviewers for their helpful feedback. This work was supported by National High Technology R&D Program of China (Grant No. 2015AA015403), Natural Science Foundation of China (Grant No. 61672057, 61672058).


  1. 1.
    Yih, W., He, X., Meek, C.: Semantic parsing for single-relation question answering. In: Meeting of the association for computational linguistics (2014)Google Scholar
  2. 2.
    Yih, W., Chang, M.-W., He, X., Gao, J.: Semantic parsing via staged query graph generation: question answering with knowledge base. In: Proceedings of ACL (2015)Google Scholar
  3. 3.
    Yu, L., Hermann, K.M., Blunsom, P., Pulman, S.: Deep learning for answer sentence selection. Computer Science (2014)Google Scholar
  4. 4.
    Yang, Y., Yih, W., Meek, C.: WikiQA: a challenge dataset for open-domain question answering. In: Proceedings of EMNLP (2015)Google Scholar
  5. 5.
    Conneau, A., Schwenk, H., Le Cun, Y., Barrault, L.: Very deep convolutional networks for text classification. In: Proceedings of EACL (2017)Google Scholar
  6. 6.
    Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. arXiv preprint arXiv: 1705.03122v2 (2017)
  7. 7.
    Yao, X., Van Durme, B.: Information extraction over structured data: question answering with freebase. In: Proceedings of ACL (2014)Google Scholar
  8. 8.
    Fader, A., Zettlemoyer, L., Etzioni, O: Open question answering over curated and extracted knowledge bases. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ACM (2014)Google Scholar
  9. 9.
    Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer Pairs. In: Proceedings of EMNLP (2013)Google Scholar
  10. 10.
    Berant, J., Liang, P.: Semantic parsing via paraphrasing. In: Proceedings of ACL (2014)Google Scholar
  11. 11.
    Liang, P., Jordan, M., Klein, D.: Learning dependency-based compositional semantics. In: Proceedings of ACL (2011)Google Scholar
  12. 12.
    Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC/ISWC-2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007). CrossRefGoogle Scholar
  13. 13.
    Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, pp. 1247–1250 (2008)Google Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of Computer Vision and Pattern Recognition (2015)Google Scholar
  16. 16.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: AAAI Conference on Artificial Intelligence (2017)Google Scholar
  17. 17.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS (2013)Google Scholar
  18. 18.
    Ye, Z., Jia, Z., Yang, Y., Huang, J., Yin, H.: Research on open domain question answering system. In: Proceedings of NLPCC (2015)Google Scholar
  19. 19.
    Lai, Y., Lin, Y., Chen, J., Feng, Y., Zhao, D.: Open domain question answering system based on knowledge base. In: Lin, C.-Y., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds.) ICCPOL/NLPCC-2016. LNCS (LNAI), vol. 10102, pp. 722–733. Springer, Cham (2016). CrossRefGoogle Scholar
  20. 20.
    Yang, F., Gan, L., Li, A., Huang, D., Chou, X., Liu, H.: Combining deep learning with information retrieval for question answering. In: Proceedings of NLPCC (2016)Google Scholar
  21. 21.
    Xie, Z., Zeng, Z., Zhou, G., He, T.: Knowledge base question answering based on deep learning models. In: Lin, C.-Y., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds.) ICCPOL/NLPCC-2016. LNCS (LNAI), vol. 10102, pp. 300–311. Springer, Cham (2016). CrossRefGoogle Scholar
  22. 22.
    Wang, L., Zhang, Y., Liu, T.: A deep learning approach for question answering over knowledge base. In: Lin, C.-Y., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds.) ICCPOL/NLPCC-2016. LNCS (LNAI), vol. 10102, pp. 885–892. Springer, Cham (2016). CrossRefGoogle Scholar
  23. 23.
    Zeiler, M.D.: ADADELTA: an adaptive learning rate method. Computer Science (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Yuxuan Lai
    • 1
    Email author
  • Yanyan Jia
    • 1
  • Yang Lin
    • 1
  • Yansong Feng
    • 1
  • Dongyan Zhao
    • 1
  1. 1.Institute of Computer Science & TechnologyPeking UniversityBeijingChina

Personalised recommendations