GENE: Global Event Network Embedding

Qi Zeng, Manling Li, Tuan Lai, Heng Ji, Mohit Bansal, Hanghang Tong


Abstract
Current methods for event representation ignore related events in a corpus-level global context. For a deep and comprehensive understanding of complex events, we introduce a new task, Event Network Embedding, which aims to represent events by capturing the connections among events. We propose a novel framework, Global Event Network Embedding (GENE), that encodes the event network with a multi-view graph encoder while preserving the graph topology and node semantics. The graph encoder is trained by minimizing both structural and semantic losses. We develop a new series of structured probing tasks, and show that our approach effectively outperforms baseline models on node typing, argument role classification, and event coreference resolution.
Anthology ID:
2021.textgraphs-1.5
Volume:
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
Month:
June
Year:
2021
Address:
Mexico City, Mexico
Editors:
Alexander Panchenko, Fragkiskos D. Malliaros, Varvara Logacheva, Abhik Jana, Dmitry Ustalov, Peter Jansen
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
42–53
Language:
URL:
https://aclanthology.org/2021.textgraphs-1.5
DOI:
10.18653/v1/2021.textgraphs-1.5
Bibkey:
Cite (ACL):
Qi Zeng, Manling Li, Tuan Lai, Heng Ji, Mohit Bansal, and Hanghang Tong. 2021. GENE: Global Event Network Embedding. In Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15), pages 42–53, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
GENE: Global Event Network Embedding (Zeng et al., TextGraphs 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.textgraphs-1.5.pdf
Code
 pkuzengqi/gene