English

Learning Constraints and Descriptive Segmentation for Subevent Detection

Computation and Language 2021-09-15 v1

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.

Keywords

Cite

@article{arxiv.2109.06316,
  title  = {Learning Constraints and Descriptive Segmentation for Subevent Detection},
  author = {Haoyu Wang and Hongming Zhang and Muhao Chen and Dan Roth},
  journal= {arXiv preprint arXiv:2109.06316},
  year   = {2021}
}

Comments

EMNLP 2021

R2 v1 2026-06-24T05:56:11.559Z