Cross-Scenario Inference Based Event-Event Relation Detection

  • Yu Hong
  • Jingli Zhang
  • Rui Song
  • Jianmin YaoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11109)


Event-Event Relation Detection (RD\(_{2e}\)) aims to detect the relations between a pair of news events, such as Causal relation between Criminal and Penal events. In general, RD\(_{2e}\) is a challenging task due to the lack of explicit linguistic feature signaling the relations. We propose a cross-scenario inference method for RD\(_{2e}\). By utilizing conceptualized scenario expression and graph-based semantic distance perception, we retrieve semantically similar historical events from Gigaword. Based on explicit relations of historical events, we infer implicit relations of target events by means of transfer learning. Experiments on 10 relation types show that our method outperforms the supervised models.


Relation detection Cross scenario Semantic distance 



This work was supported by the national Natural Science Foundation of China via Nos. 2017YFB1002104, 61672368 and 61672367.


  1. 1.
    Abe, S., Inui, K., Matsumoto, Y.: Acquiring event relation knowledge by learning cooccurrence patterns and fertilizing cooccurrence samples with verbal nouns. In: IJCNLP, pp. 497–504 (2008)Google Scholar
  2. 2.
    Abe, S., Inui, K., Matsumoto, Y.: Two-phased event relation acquisition: coupling the relation-oriented and argument-oriented approaches. In: COLING, pp. 1–8 (2008)Google Scholar
  3. 3.
    Blanco, E., Castell, N., Moldovan, D.I.: Causal relation extraction. In: LREC (2008)Google Scholar
  4. 4.
    Caselli, T., Fokkens, A., Morante, R., Vossen, P.: Spinoza vu: an NLP pipeline for cross document timelines. In: SemEval-2015 p. 787 (2015)Google Scholar
  5. 5.
    Chang, D.-S., Choi, K.-S.: Causal relation extraction using cue phrase and lexical pair probabilities. In: Su, K.-Y., Tsujii, J., Lee, J.-H., Kwong, O.Y. (eds.) IJCNLP 2004. LNCS (LNAI), vol. 3248, pp. 61–70. Springer, Heidelberg (2005). Scholar
  6. 6.
    Do, Q.X., Chan, Y.S., Roth, D.: Minimally supervised event causality identification. In: EMNLP, pp. 294–303 (2011)Google Scholar
  7. 7.
    Gildea, D., Palmer, M.: The necessity of parsing for predicate argument recognition. In: ACL, pp. 239–246 (2002)Google Scholar
  8. 8.
    Girju, R., Moldovan, D.I., et al.: Text mining for causal relations. In: FLAIRS, pp. 360–364 (2002)Google Scholar
  9. 9.
    Hong, Y., Zhang, T., O’Gorman, T., Horowit-Hendler, S., Ji, H., Palmer, M.: Building a cross-document event-event relation corpus. In: LAW X, p. 1 (2016)Google Scholar
  10. 10.
    Inui, T., Inui, K., Matsumoto, Y.: Acquiring causal knowledge from text using the connective marker tame. TALIP 4(4), 435–474 (2005)CrossRefGoogle Scholar
  11. 11.
    Ittoo, A., Bouma, G.: Extracting explicit and implicit causal relations from sparse, domain-specific texts. In: Muñoz, R., Montoyo, A., Métais, E. (eds.) NLDB 2011. LNCS, vol. 6716, pp. 52–63. Springer, Heidelberg (2011). Scholar
  12. 12.
    Lapata, M., Lascarides, A.: Learning sentence-internal temporal relations. J. Artif. Intell. Res. (JAIR) 27, 85–117 (2006)CrossRefGoogle Scholar
  13. 13.
    Lin, Z., Ng, H.T., Kan, M.Y.: A PDTB-styled end-to-end discourse parser. Nat. Lang. Eng. 20(02), 151–184 (2014)CrossRefGoogle Scholar
  14. 14.
    Mani, I., Verhagen, M., Wellner, B., Lee, C.M., Pustejovsky, J.: Machine learning of temporal relations. In: COLING and ACL, pp. 753–760 (2006)Google Scholar
  15. 15.
    Migon, H.S., Gamerman, D., Louzada, F.: Statistical inference: an integrated approach. CRC Press, Boca Raton (2014)zbMATHGoogle Scholar
  16. 16.
    Minard, A.L., et al.: Semeval-2015 task 4: Timeline: Cross-document event ordering. In: SemEval, pp. 778–786 (2015)Google Scholar
  17. 17.
    Miwa, M., Bansal, M.: End-to-end relation extraction using lstms on sequences and tree structures (2016). arXiv preprint. arXiv:1601.00770
  18. 18.
    Pitler, E., Louis, A., Nenkova, A.: Automatic sense prediction for implicit discourse relations in text. In: ACL and AFNLP, pp. 683–691 (2009)Google Scholar
  19. 19.
    Prasad, R., et al.: The penn discourse treebank 2.0. In: LREC (2008)Google Scholar
  20. 20.
    Pustejovsky, J., Verhagen, M.: Semeval-2010 task 13: evaluating events, time expressions, and temporal relations (tempeval-2). In: Workshop on Semantic Evaluations, pp. 112–116 (2009)Google Scholar
  21. 21.
    Radinsky, K., Davidovich, S., Markovitch, S.: Learning causality for news events prediction. In: WWW, pp. 909–918 (2012)Google Scholar
  22. 22.
    Raja, K., Subramani, S., Natarajan, J.: Ppinterfinder–a mining tool for extracting causal relations on human proteins from literature. Database 2013, bas052 (2013)Google Scholar
  23. 23.
    Rugemalira, J.M.: What is a symmetrical language? multiple object constructions in Bantu. In: Berkeley Linguistics Society, vol. 17 (2012)Google Scholar
  24. 24.
    Santos, C.N.d., Xiang, B., Zhou, B.: Classifying relations by ranking with convolutional neural networks (2015). arXiv preprint arXiv:1504.06580
  25. 25.
    Velupillai, S., Mowery, D.L., Abdelrahman, S., Christensen, L., Chapman, W.W.: Blulab: Temporal information extraction for the 2015 clinical tempeval challenge. In: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pp. 815-819 (2015)Google Scholar
  26. 26.
    Zhou, Z.M., Xu, Y., Niu, Z.Y., Lan, M., Su, J., Tan, C.L.: Predicting discourse connectives for implicit discourse relation recognition. In: COLING, pp. 1507–1514 (2010)Google Scholar
  27. 27.
    Zou, B., Zhou, G., Zhu, Q.: Tree kernel-based negation and speculation scope detection with structured syntactic parse features. In: EMNLP, pp. 968–976 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Computer Information Processing Technology of Soochow UniversitySuzhouChina

Personalised recommendations