Learning Constraints and Descriptive Segmentation for Subevent Detection

Haoyu Wang, Hongming Zhang, Muhao Chen, Dan Roth


Abstract
Event mentions in text correspond to real-world events of varying degrees of granularity. The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes. Since knowing the span of descriptive contexts of event complexes helps infer the membership of events, we propose the task of event-based text segmentation (EventSeg) as an auxiliary task to improve the learning for subevent detection. To bridge the two tasks together, we propose an approach to learning and enforcing constraints that capture dependencies between subevent detection and EventSeg prediction, as well as guiding the model to make globally consistent inference. Specifically, we adopt Rectifier Networks for constraint learning and then convert the learned constraints to a regularization term in the loss function of the neural model. Experimental results show that the proposed method outperforms baseline methods by 2.3% and 2.5% on benchmark datasets for subevent detection, HiEve and IC, respectively, while achieving a decent performance on EventSeg prediction.
Anthology ID:
2021.emnlp-main.423
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5216–5226
Language:
URL:
https://aclanthology.org/2021.emnlp-main.423
DOI:
10.18653/v1/2021.emnlp-main.423
Bibkey:
Cite (ACL):
Haoyu Wang, Hongming Zhang, Muhao Chen, and Dan Roth. 2021. Learning Constraints and Descriptive Segmentation for Subevent Detection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5216–5226, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Learning Constraints and Descriptive Segmentation for Subevent Detection (Wang et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.423.pdf