Corpus-based Open-Domain Event Type Induction

Jiaming Shen, Yunyi Zhang, Heng Ji, Jiawei Han


Abstract
Traditional event extraction methods require predefined event types and their corresponding annotations to learn event extractors. These prerequisites are often hard to be satisfied in real-world applications. This work presents a corpus-based open-domain event type induction method that automatically discovers a set of event types from a given corpus. As events of the same type could be expressed in multiple ways, we propose to represent each event type as a cluster of <predicate sense, object head> pairs. Specifically, our method (1) selects salient predicates and object heads, (2) disambiguates predicate senses using only a verb sense dictionary, and (3) obtains event types by jointly embedding and clustering <predicate sense, object head> pairs in a latent spherical space. Our experiments, on three datasets from different domains, show our method can discover salient and high-quality event types, according to both automatic and human evaluations.
Anthology ID:
2021.emnlp-main.441
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5427–5440
Language:
URL:
https://aclanthology.org/2021.emnlp-main.441
DOI:
10.18653/v1/2021.emnlp-main.441
Bibkey:
Cite (ACL):
Jiaming Shen, Yunyi Zhang, Heng Ji, and Jiawei Han. 2021. Corpus-based Open-Domain Event Type Induction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5427–5440, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Corpus-based Open-Domain Event Type Induction (Shen et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.441.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.441.mp4
Code
 mickeystroller/etypeclus
Data
Word Sense Disambiguation: a Unified Evaluation Framework and Empirical Comparison