UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning

Zhengwei Tao, Zhi Jin, Haiyan Zhao, Chengfeng Dou, Yongqiang Zhao, Tao Shen, Chongyang Tao


Abstract
Reasoning about events and their relations attracts surging research efforts since it is regarded as an indispensable ability to fulfill various event-centric or common-sense reasoning tasks. However, these tasks often suffer from limited data availability due to the labor-intensive nature of their annotations. Consequently, recent studies have explored knowledge transfer approaches within a multi-task learning framework to address this challenge. Although such methods have achieved acceptable results, such brute-force solutions struggle to effectively transfer event-relational knowledge due to the vast array of inter-event relations (e.g. temporal, causal, conditional) and reasoning formulations (e.g. discriminative, abductive, ending prediction). To enhance knowledge transfer and enable zero-shot generalization among various combinations, in this work we propose a novel unified framework, called UNIEVENT. Inspired by prefix-based multitask learning, our approach organizes event relational reasoning tasks into a coordinate system with multiple axes, representing inter-event relations and reasoning formulations. We then train a unified text-to-text generative model that utilizes coordinate-assigning prefixes for each task. By leveraging our adapted prefixes, our unified model achieves state-of-the-art or competitive performance on both zero-shot and supervised reasoning tasks, as demonstrated in extensive experiments
Anthology ID:
2023.acl-long.391
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7088–7102
Language:
URL:
https://aclanthology.org/2023.acl-long.391
DOI:
10.18653/v1/2023.acl-long.391
Bibkey:
Cite (ACL):
Zhengwei Tao, Zhi Jin, Haiyan Zhao, Chengfeng Dou, Yongqiang Zhao, Tao Shen, and Chongyang Tao. 2023. UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7088–7102, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning (Tao et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.391.pdf
Video:
 https://aclanthology.org/2023.acl-long.391.mp4