Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks

Pengfei Cao, Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao, Yuguang Chen, Weihua Peng


Abstract
Identifying causal relations of events is an important task in natural language processing area. However, the task is very challenging, because event causality is usually expressed in diverse forms that often lack explicit causal clues. Existing methods cannot handle well the problem, especially in the condition of lacking training data. Nonetheless, humans can make a correct judgement based on their background knowledge, including descriptive knowledge and relational knowledge. Inspired by it, we propose a novel Latent Structure Induction Network (LSIN) to incorporate the external structural knowledge into this task. Specifically, to make use of the descriptive knowledge, we devise a Descriptive Graph Induction module to obtain and encode the graph-structured descriptive knowledge. To leverage the relational knowledge, we propose a Relational Graph Induction module which is able to automatically learn a reasoning structure for event causality reasoning. Experimental results on two widely used datasets indicate that our approach significantly outperforms previous state-of-the-art methods.
Anthology ID:
2021.acl-long.376
Original:
2021.acl-long.376v1
Version 2:
2021.acl-long.376v2
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4862–4872
Language:
URL:
https://aclanthology.org/2021.acl-long.376
DOI:
10.18653/v1/2021.acl-long.376
Bibkey:
Cite (ACL):
Pengfei Cao, Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao, Yuguang Chen, and Weihua Peng. 2021. Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4862–4872, Online. Association for Computational Linguistics.
Cite (Informal):
Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks (Cao et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.376.pdf
Video:
 https://aclanthology.org/2021.acl-long.376.mp4