Event Causality Identification by Modeling Events and Relation Embedding

  • Zhenyu Yang
  • Wei LiuEmail author
  • Zongtian Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11303)


Events and event relations contain high-level semantic information behind texts. In this paper, we mainly discuss event causality relation identification. Traditional approaches of causality relation identification rely on the recognition of casual relationship connectives or manual features of causality relationships, and these methods have disadvantage of low recognition coverage and being lack of adaptive. To solve this problem, we propose a novel model based on modeling event and event relation. We use word sequence around event trigger as input data and use event based Siamese Bi-LSTM network to model events by encoding the event representations into a fixed size vectors, and then these events representations are applied in relation embedding training and prediction. Experimental results show that the proposed method can achieve better effect on CEC 2.0 corpus.


Siamese network Event relation LSTM CEC 


  1. 1.
    Liu, Z.T., et al.: Research on event-oriented ontology model. Comput. Sci. 36(11), 189–192 (2009)Google Scholar
  2. 2.
    Chopra, S., Hadsell, R., Lecun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), pp. 539–546. IEEE, Piscataway (2005)Google Scholar
  3. 3.
    Norouzi, M., Fleet, D.J., Salakhutdinov, R.R.: Hamming distance metric learning. In: Advances in Neural Information Processing Systems, pp. 1061–1069. Curran Associates, New York (2012)Google Scholar
  4. 4.
    Baraldi L., Grana C., Cucchiara R.: A deep siamese network for scene detection in broadcast videos. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1199–1202. ACM, New York (2015)Google Scholar
  5. 5.
    Kenter, T., Borisov, A., de Rijke, M.: Siamese CBOW: optimizing word embeddings for sentence representations (2016). arXiv preprint: arXiv:1606.04640
  6. 6.
    Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: Thirtieth AAAI Conference on Artificial Intelligence, pp. 2786–2792. AAAI, Menlo Park (2016)Google Scholar
  7. 7.
    Garcia, D.: COATIS, an NLP system to locate expressions of actions connected by causality links. In: Plaza, E., Benjamins, R. (eds.) EKAW 1997. LNCS, vol. 1319, pp. 347–352. Springer, Heidelberg (1997). Scholar
  8. 8.
    Khoo, C.S.G., Kornfilt, J., Oddy, R.N., Myaeng, S.H.: Automatic extraction of cause-effect information from newspaper text without knowledge-based inferencing. Literary Linguist. Comput. 13(4), 177–186 (1998)CrossRefGoogle Scholar
  9. 9.
    Girju, R.: Automatic detection of causal relations for question answering. In: Proceedings of the ACL 2003 Workshop on Multilingual Summarization and Question Answering, vol. 12, pp. 76–83. ACL, Stroudsburg (2003)Google Scholar
  10. 10.
    Marcu, D., Echihabi, A.: An unsupervised approach to recognizing discourse relations. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 368–375. ACL, Stroudsburg (2002)Google Scholar
  11. 11.
    Inui, T., Inui, K., Matsumoto, Y.: What kinds and amounts of causal knowledge can be acquired from text by using connective markers as clues? In: Grieser, G., Tanaka, Y., Yamamoto, A. (eds.) DS 2003. LNCS (LNAI), vol. 2843, pp. 180–193. Springer, Heidelberg (2003). Scholar
  12. 12.
    Zhong, J., Long, Y., Tian, S.: Causal relation extraction of uyghur emergency events based on cascaded model. Zidonghua Xuebao/Acta Autom. Sin. 40(4), 771–779 (2014)Google Scholar
  13. 13.
    Fu, J., Liu, Z., Liu, W.: Using dual-layer CRFs for event causal relation extraction. IEICE Electron. Express 8(5), 306–310 (2011)CrossRefGoogle Scholar
  14. 14.
    Yang, J., Liu, Z., Liu, W.: Identify causality relationships based on semantic event. J. Chin. Comput. Syst. 36(3), 433–437 (2016)Google Scholar
  15. 15.
    Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: International Conference on Neural Information Processing Systems, pp. 2787–2795. Curran Associates, New York (2013)Google Scholar
  16. 16.
    Wang, Z., Zhang, J., Feng J.: Knowledge graph embedding by translating on hyperplanes. In: AAAI - Association for the Advancement of Artificial Intelligence, pp. 1112–1119. AAAI, Menlo Park (2014)Google Scholar
  17. 17.
    Ji, G., He, S., Xu, L.: Knowledge graph embedding via dynamic mapping matrix. In: Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, pp. 687–696. ACL, Stroudsburg (2015)Google Scholar
  18. 18.
    Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of the 31st International Conference on Machine Learning, pp. 1188–1196. JMLR (2014)Google Scholar
  19. 19.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). arXiv preprint: arXiv:1301.3781
  20. 20.
    Fu, J., Liu, Z., Zhong, Z.: Chinese event extraction based on feature weighting. Inf. Technol. J. 9(1), 184–187 (2010)CrossRefGoogle Scholar
  21. 21.
    Zhao, Y., Qin, B., Che, W., Liu, T.: Research on Chinese event extraction. J. Chin. Inf. Process. 22(1), 3–8 (2008)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Computer Engineering and ScienceShanghai UniversityShanghaiChina

Personalised recommendations