Logo PTI
Polish Information Processing Society
Logo FedCSIS

Annals of Computer Science and Information Systems, Volume 11

Proceedings of the 2017 Federated Conference on Computer Science and Information Systems

Event Relation Acquisition Using Dependency Patterns and Confidence-Weighted Co-occurrence Statistics

, , ,

DOI: http://dx.doi.org/10.15439/2017F419

Citation: Proceedings of the 2017 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 11, pages 339–345 ()

Full text

Abstract. Event relation knowledge is important for deep language understanding and inference. Previous work has established automatic acquisition methods of event relations that focus on common sense knowledge acquisition from large-scale unlabeled corpus. However, in the case of domain-specific knowledge acquisition, such a method can not acquire much knowledge due to the limited amount of available knowledge sources. We propose an coverage-oriented acquisition method of event relations. The proposed method utilizes various patterns of dependency structures co-occurring with event relations than the existing method relying only on direct dependency relations between events. Experimental results show that the proposed method can acquire a larger amount of positive relation instances while keeping higher precision compared with the existing method and the proposed method also performs well for small sizes of corpora.

References

  1. S. Abe, K. Inui, and Y. Matsumoto, “Two-phased event relation acquisition: coupling the relation-oriented and argument-oriented approaches,” in Proceedings of the 22nd International Conference on Computational Linguistics (COLING), 2008. http://dx.doi.org/10.3115/1599081.1599082 pp. 1–8. [Online]. Available: http://dx.doi.org/10.3115/1599081.1599082
  2. T. Chklovski and P. Pantel, “VerbOcean: Mining the web for fine-grained semantic verb relations,” in Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP), vol. 4, 2004, pp. 33–40.
  3. Q. X. Do, Y. S. Chan, and D. Roth, “Minimally supervised event causality identification,” in Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2011, pp. 294–303.
  4. C. Hashimoto, K. Torisawa, K. Kuroda, S. De Saeger, M. Murata, and J. Kazama, “Large-scale verb entailment acquisition from the web,” in Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3-Volume 3. Association for Computational Linguistics, 2009, pp. 1172–1181.
  5. D. Lin and P. Pantel, “Dirt - discovery of inference rules from text,” in Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining (KDD), 2001. http://dx.doi.org/10.1145/502512.502559 pp. 323–328. [Online]. Available: http://dx.doi.org/10.1145/502512.502559
  6. T. Shibata and S. Kurohashi, “Acquiring strongly-related events using predicate-argument co-occurring statistics and case frames,” in Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP), 2011, pp. 1028–1036.
  7. K. Torisawa, “Acquiring inference rules with temporal constraints by using japanese coordinated sentences and noun-verb co-occurrences,” in Proceedings of Human Language Technology conference / North American chapter of the Association for Computational Linguistics annual meeting (HLT-NAACL), 2006. http://dx.doi.org/10.3115/1220835.1220843 pp. 57–64.
  8. H. Weisman, J. Berant, I. Szpektor, and I. Dagan, “Learning verb inference rules from linguistically-motivated evidence,” in Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), 2012, pp. 194–204.
  9. C. Hashimoto, K. Torisawa, J. Kloetzer, M. Sano, I. Varga, J.-H. Oh, and Y. Kidawara, “Toward future scenario generation: Extracting event causality exploiting semantic relation, context, and association features.” in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), 2014, pp. 987–997.
  10. J. Kloetzer, K. Torisawa, C. Hashimoto, and J.-H. Oh, “Large-scale acquisition of entailment pattern pairs by exploiting transitivity,” in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015, pp. 1649–1655.
  11. N. Chambers and D. Jurafsky, “Unsupervised learning of narrative event chains,” in Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL), vol. 94305, 2008, pp. 789–797.
  12. N. Chambers and D. Jurafsky, “Unsupervised learning of narrative schemas and their participants,” in Proceedings of Joint conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP), 2009. http://dx.doi.org/10.3115/1690219.1690231 pp. 602–610.
  13. K. Pichotta and R. J. Mooney, “Statistical script learning with multi-argument events,” in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL), vol. 14, 2014. http://dx.doi.org/10.3115/v1/e14-1024 pp. 220–229.
  14. M. Granroth-Wilding and S. Clark, “What happens next? event prediction using a compositional neural network model,” in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI), 2016, pp. 2727–2733.
  15. K. Pichotta and R. J. Mooney, “Learning statistical scripts with lstm recurrent neural networks,” in Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI), 2016, pp. 2800–2806.
  16. S. Abe, K. Inui, and Y. Matsumoto, “Acquiring event relation knowledge by learning cooccurrence patterns and fertilizing cooccurrence samples (in Japanese),” Journal of Natural Language Processing, vol. 16, no. 5, pp. 79–100, 2009. http://dx.doi.org/10.5715/jnlp.16.5_79. [Online]. Available: http://dx.doi.org/10.5715/jnlp.16.5\_79
  17. P. Pantel and D. Ravichandran, “Automatically labeling semantic classes,” in Proceedings of Human Language Technology conference / North American chapter of the Association for Computational Linguistics annual meeting (HLT-NAACL), vol. 4, 2004, pp. 321–328.
  18. T. Kudo and Y. Matsumoto, “Japanese dependency analysis using cascaded chunking,” in Proceedings of the Conference on Computational Natural Language Learning (CoNLL-2002), 2002. http://dx.doi.org/10.3115/1118853.1118869 pp. 63–69. [Online]. Available: http://dx.doi.org/10.3115/1118853.1118869