Abstract
Event Argument Extraction (EAE) is the task of identifying roles of entity mentions/arguments in events evoked by trigger words. Most existing works have focused on sentence-level EAE, leaving document-level EAE (i.e., event triggers and arguments belong to different sentences in documents) an under-studied problem in the literature. This paper introduces a new deep learning model for document-level EAE where document structures/graphs are utilized to represent input documents and aid the representation learning. Our model employs different types of interactions between important context words in documents (i.e., syntax, semantic, and discourse) to enhance document representations. Extensive experiments are conducted to demonstratethe effectiveness of the proposed model, leading to the state-of-the-art performance for document-level EAE.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
We use the Stanford Core NLP Toolkit to parse the sentences in this work.
- 3.
We use the Stanford Core NLP Toolkit to determine the coreference of entity mentions.
References
Blevins, T., Zettlemoyer, L.: Moving down the long tail of word sense disambiguation with gloss informed bi-encoders. In: ACL (2020)
Christopoulou, F., Miwa, M., Ananiadou, S.: Connecting the dots: document-level neural relation extraction with edge-oriented graphs. In: EMNLP (2019)
Ebner, S., Xia, P., Culkin, R., Rawlins, K., Van Durme, B.: Multi-sentence argument linking. In: ACL (2020)
Gerber, M., Chai, J.Y.: Semantic role labeling of implicit arguments for nominal predicates. In: Computational Linguistics (2012)
Gupta, P., Rajaram, S., Schütze, H., Runkler, T.: Neural relation extraction within and across sentence boundaries. In: AAAI (2019)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Lai, V.D., Nguyen, T.N., Nguyen, T.H.: Event detection: gate diversity and syntactic importance scores for graph convolution neural networks. In: EMNLP (2020)
Le, D.M., Nguyen, T.H.: Fine-grained event trigger detection. In: EACL (2021)
Li, Q., Ji, H., Huang, L.: Joint event extraction via structured prediction with global features. In: ACL (2013)
Nan, G., Guo, Z., Sekulic, I., Lu, W.: Reasoning with latent structure refinement for document-level relation extraction. In: ACL (2020)
Nguyen, T.H., Cho, K., Grishman, R.: Joint event extraction via recurrent neural networks. In: NAACL-HLT (2016)
Nguyen, T.M., Nguyen, T.H.: One for all: neural joint modeling of entities and events. In: AAAI (2019)
Ben Veyseh, A.P., Nguyen, T.N., Nguyen, T.H.: Graph transformer networks with syntactic and semantic structures for event argument extraction. In: EMNLP Findings (2020)
Sahu, S.K., Christopoulou, F., Miwa, M., Ananiadou, S.: Inter-sentence relation extraction with document-level graph convolutional neural network. In: ACL (2019)
Thayaparan, M., Valentino, M., Schlegel, V., Freitas, A.: Identifying supporting facts for multi-hop question answering with document graph networks. In: The Thirteenth Workshop on Graph-Based Methods for Natural Language Processing at EMNLP (2019)
Tran, H.M., Nguyen, M.T., Nguyen, T.H.: The dots have their values: exploiting the node-edge connections in graph-based neural models for document-level relation extraction. In: EMNLP Findings (2020)
Wang, X., et al.: HMEAE: hierarchical modular event argument extraction. In: EMNLP-IJCNLP (2019)
Yun, S., Jeong, M., Kim, R., Kang, J., Kim, H.J.: Graph transformer networks. In: NeurIPS (2019)
Zhang, Z., Kong, X., Liu, Z., Ma, X., Hovy, E.: A two-step approach for implicit event argument detection. In: ACL (2020)
Acknowledgments
This research has been supported by Vingroup Innovation Foundation (VINIF) in project VINIF.2019.DA18 and Army Research Office (ARO) grant W911NF-17-S-0002. This research is also based upon work supported by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA Contract No. 2019-19051600006 under the Better Extraction from Text Towards Enhanced Retrieval (BETTER) Program. The views contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of ARO, ODNI, IARPA, the Department of Defense, or the U.S. Government.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Veyseh, A.P.B. et al. (2021). Inducing Rich Interaction Structures Between Words for Document-Level Event Argument Extraction. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12713. Springer, Cham. https://doi.org/10.1007/978-3-030-75765-6_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-75765-6_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75764-9
Online ISBN: 978-3-030-75765-6
eBook Packages: Computer ScienceComputer Science (R0)