Abstract
Event information is of great value, but the exploitation of it generally relies on not only extracting events from the text, but also figuring out the relations among events and organizing them accordingly. In this paper, based on a more flexible and practical type of event relation called the plot relation, we study the method of automatic event relation recognition. Specifically, we propose a local prediction method by using diversified linguistic and temporal features. Furthermore, we design a joint reasoning framework, in which we leverage the information of participants and locations, and add global constraints to further improve the performance. Finally, we transform the proposed model into integer linear programming (ILP) to obtain the global optimum. Our experiments demonstrate that our method significantly outperforms all the existing methods.
This work is supported by the National Natural Science Foundation of China (No. 61872172), the Open Project Program of the State Key Laboratory of Mathematical Engineering and Advanced Computing, and the Fundamental Research Funds for the Central Universities (No. 020214380064).
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
Notes
- 1.
The eight subtasks: relevant sentence selection, event detection, timex detection and normalization, event participant detection, event coreference resolution, temporal relation detection, plot relation recognition and climax event identification.
- 2.
{BEFORE, BEFORE_OVERLAP, BEGINS_ON, ENDS_ON}\(\mapsto \) before, {AFTER, AFTER_OVERLAP, BEGUN_ON, ENDED_ON}\(\mapsto \) after, {CONTAINS}\(\mapsto \) include, Â {IS_CONTAINED}\(\mapsto \) is_included,{OVERLAP, SIMULTANEOUS}\(\mapsto \) simultaneous, Â {VAGUE}\(\mapsto \) vague.
- 3.
Training set: T5, T7, T8, T32, T33, T35. Test set: T1, T3, T4, T12, T13, T14, T16, T18, T19, T20, T22, T23, T24, T30, T37, T41.
- 4.
References
Caselli, T., Inel, O.: Crowdsourcing storylines: harnessing the crowd for causal relation annotation. In: COLING 2018 Workshop on Events and Stories in the News. Santa Fe, NM, USA, pp. 44–54 (2018)
Caselli, T., Vossen, P.: The storyline annotation and representation scheme (StaR): a proposal. In: EMNLP 2016 Workshop on Computing News Storylines. Austin, TX, USA, pp. 67–72 (2016)
Caselli, T., Vossen, P.: The event storyline corpus: a new benchmark for causal and temporal relation extraction. In: ACL 2017 Workshop on Events and Stories in the News. Vancouver, Canada, pp. 77–86 (2017)
Chambers, N., Cassidy, T., McDowell, B., Bethard, S.: Dense event ordering with a multi-pass architecture. Trans. Assoc. Comput. Linguist. 2, 273–284 (2014)
Cybulska, A., Vossen, P.: Guidelines for ECB+ annotation of events and their coreference. Tech. rep., Technical Report NWR-2014-1, VU University Amsterdam (2014)
Do, Q.X., Lu, W., Roth, D.: Joint inference for event timeline construction. In: EMNLP, pp. 677–687 (2012)
Gao, L., Choubey, P.K., Huang, R.: Modeling document-level causal structures for event causal relation identification. In: NAACL-HLT. Minneapolis, Minnesota, pp. 1808–1817 (2019)
Hanawa, K., Sasaki, A., Okazaki, N., Inui, K.: A crowdsourcing approach for annotating causal relation instances in wikipedia. In: Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation, pp. 336–345 (2017)
Hu, P., Huang, M., Zhu, X.: Exploring the interactions of storylines from informative news events. J. Comput. Sci. Technol. 29(3), 502–518 (2014)
Huang, L.: Optimized event storyline generation based on mixture-event-aspect model. In: EMNLP. Seattle, WA, USA, pp. 726–735 (2013)
Kruengkrai, C., Torisawa, K., Hashimoto, C., Kloetzer, J., Oh, J.H., Tanaka, M.: Improving event causality recognition with multiple background knowledge sources using multi-column convolutional neural networks. In: AAAI, pp. 3466–3473 (2017)
Li, P., Mao, K.: Knowledge-oriented convolutional neural network for causal relation extraction from natural language texts. Expert Syst. Appl. 115, 512–523 (2019)
Mirza, P., Tonelli, S.: CATENA: CAusal and TEmporal relation extraction from NAtural language texts. In: COLING 2016. Osaka, Japan, pp. 64–75 (2016)
Mostafazadeh, N., Grealish, A., Chambers, N., Allen, J., Vanderwende, L.: Caters: causal and temporal relation scheme for semantic annotation of event structures. In: Proceedings of the Fourth Workshop on Events, pp. 51–61 (2016)
Ning, Q., Feng, Z., Roth, D.: A structured learning approach to temporal relation extraction. In: EMNLP. Copenhagen, Denmark, pp. 1027–1037 (2017)
Ning, Q., Feng, Z., Wu, H., Roth, D.: Joint reasoning for temporal and causal relations. In: ACL. Melbourne, Australia, pp. 2278–2288 (2018)
Reimers, N., Dehghani, N., Gurevych, I.: Event time extraction with a decision tree of neural classifiers. Trans. Assoc. Comput. Linguist. 6, 77–89 (2018)
Shahaf, D., Yang, J., Suen, C., Jacobs, J., Wang, H., Leskovec, J.: Information cartography: creating zoomable, large-scale maps of information. In: KDD. Chicago, IL, USA, pp. 1097–1105 (2013)
Vossen, P., Caselli, T., Kontzopoulou, Y.: Storylines for structuring massive streams of news. In: ACL 2015 Workshop on Computing News Storylines. Beijing, China, pp. 40–49 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Qiu, S., Yu, B., Qian, L., Guo, Q., Hu, W. (2020). Joint Reasoning of Events, Participants and Locations for Plot Relation Recognition. In: Wang, X., Zhang, R., Lee, YK., Sun, L., Moon, YS. (eds) Web and Big Data. APWeb-WAIM 2020. Lecture Notes in Computer Science(), vol 12317. Springer, Cham. https://doi.org/10.1007/978-3-030-60259-8_51
Download citation
DOI: https://doi.org/10.1007/978-3-030-60259-8_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60258-1
Online ISBN: 978-3-030-60259-8
eBook Packages: Computer ScienceComputer Science (R0)