Abstract
Currently, Chinese argument extraction mainly focuses on feature engineering, which cannot exploit inner relationships between event mentions in the same document. To address this issue, this paper learns the probabilities of entities fulfilling a specific role from the training set and the relationship among events to infer more arguments using Markov Logic Networks. Experimental results on the ACE 2005 Chinese corpus show that our approach outperforms the baseline significantly, with an improvement of 8.6% and 8.2% in argument identification and role determination respectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Linguistic Data Consortium. ACE (Automatic Content Extraction) Chinese Annotation Guidelines for Events. 2009–09–08. Version5.5.1. http://www.ldc.upenn.edu/Projects/
Zhao, Y.Y., Qin, B., Che, W., et al.: Research on Chinese event extraction. Journal of Chinese Information Processing 22(1), 3–8 (2008). (in Chinese)
Tan, H.Y.: Research on Chinese event extraction. Harbin Institute of Technology (2008). (in Chinese)
Li, P., Zhou, G., Zhu, Q., Hou, L.: Employing compositional semantics and discourse consistency in chinese event extraction. In: Proc. EMNLP 2012, pp. 1006–1016, Jeju, Korea (2012a)
Hou, L.B., Li, P.F., Zhu, Q.M.: Study of Event Recognition Based on CRFs and Cross-event. Jisuanji Gongcheng/ Computer Engineering 38(24) (2012). (in Chinese)
Chen, Z., Ji, H.: Language specific issue and feature exploration in Chinese event extraction. In: Proceeding of the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics Boulder, Colorado, USA, pp. 209–212 (2009)
Ahn, D.: The stages of event extraction. In: Proceedings of the Workshop on Annotations and Reasoning about Time and Events, pp. 1–8 (2006)
Fu, J., Liu, Z., Zhong, Z., Shan, J.: Chinese Event Extraction Based on Feature Weighting. Information Technology Journal 9, 184–187 (2010)
Li, P., Zhou, G., Zhu, Q.: Argument inference from relevant event mentions in chinese argument extraction. In: Proceedings of ACL, pp. 1477–1487 (2013)
Liao, S., Grishman, R.: Using document level cross-event inference to improve event extraction. In: Porc. ACL–2010, Uppsala, Sweden, July, pp. 789–797 (2010)
Yu, H., Zhang, J., Ma, B., at el.: Using cross-entity inference to improve event extraction. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 1127–1136 (2011)
Li, P., Zhou, G.: Employing morphological structures and sememes for chinese event extraction. In: COLING, pp. 1619–1634 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Zhu, S., Li, P., Zhu, Q. (2015). A Chinese Event Argument Inference Approach Based on Entity Semantics and Event Relevance. In: Lu, Q., Gao, H. (eds) Chinese Lexical Semantics. CLSW 2015. Lecture Notes in Computer Science(), vol 9332. Springer, Cham. https://doi.org/10.1007/978-3-319-27194-1_58
Download citation
DOI: https://doi.org/10.1007/978-3-319-27194-1_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27193-4
Online ISBN: 978-3-319-27194-1
eBook Packages: Computer ScienceComputer Science (R0)