Efficient Zero-shot Event Extraction with Context-Definition Alignment

Hongming Zhang, Wenlin Yao, Dong Yu


Abstract
Event extraction (EE) is the task of identifying interested event mentions from text.Conventional efforts mainly focus on the supervised setting. However, these supervised models cannot generalize to event types out of the pre-defined ontology. To fill this gap, many efforts have been devoted to the zero-shot EE problem. This paper follows the trend of modeling event-type semantics but moves one step further. We argue that using the static embedding of the event type name might not be enough because a single word could be ambiguous, and we need a sentence to define the type semantics accurately. To model the definition semantics, we use two separate transformer models to project the contextualized event mentions and corresponding definitions into the same embedding space and then minimize their embedding distance via contrastive learning. On top of that, we also propose a warming phase to help the model learn the minor difference between similar definitions. We name our approach Zero-shot Event extraction with Definition (ZED). Experiments on the MAVEN dataset show that our model significantly outperforms all previous zero-shot EE methods with fast inference speed due to the disjoint design. Further experiments also show that can be easily applied to the few-shot setting when the annotation is available and consistently outperforms baseline supervised methods.
Anthology ID:
2022.findings-emnlp.531
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7169–7179
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.531
DOI:
10.18653/v1/2022.findings-emnlp.531
Bibkey:
Cite (ACL):
Hongming Zhang, Wenlin Yao, and Dong Yu. 2022. Efficient Zero-shot Event Extraction with Context-Definition Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 7169–7179, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Efficient Zero-shot Event Extraction with Context-Definition Alignment (Zhang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.531.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.531.mp4