Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction
Senhui Zhang, Tao Ji, Wendi Ji, Xiaoling Wang
Abstract
Event detection is a classic natural language processing task. However, the constantly emerging new events make supervised methods not applicable to unseen types. Previous zero-shot event detection methods either require predefined event types as heuristic rules or resort to external semantic analyzing tools. To overcome this weakness, we propose an end-to-end framework named Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction (ZEOP). By creatively introducing multiple contrastive samples with ordered similarities, the encoder can learn event representations from both instance-level and class-level, which makes the distinctions between different unseen types more significant. Meanwhile, we utilize the prompt-based prediction to identify trigger words without relying on external resources. Experiments demonstrate that our model detects events more effectively and accurately than state-of-the-art methods.
BibTeX
@inproceedings{zhang-etal-2022-zero,
title = "Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction",
author = "Zhang, Senhui and
Ji, Tao and
Ji, Wendi and
Wang, Xiaoling",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.196/",
doi = "10.18653/v1/2022.findings-naacl.196",
pages = "2572--2580"
}