Graph Learning Regularization and Transfer Learning for Few-Shot Event Detection

Viet Dac Lai, Minh Van Nguyen, Thien Huu Nguyen, Franck Dernoncourt

Abstract

We address the poor generalization of few-shot learning models for event detection (ED) using transfer learning and representation regularization. In particular, we propose to transfer knowledge from open-domain word sense disambiguation into few-shot learning models for ED to improve their generalization to new event types. We also propose a novel training signal derived from dependency graphs to regularize the representation learning for ED. Moreover, we evaluate few-shot learning models for ED with a large-scale human-annotated ED dataset to obtain more reliable insights for this problem. Our comprehensive experiments demonstrate that the proposed model outperforms state-of-the-art baseline models in the few-shot learning and supervised learning settings for ED. Code and data splits are available at https://github.com/laiviet/ed-fsl.
BibTeX
@inproceedings{lai2021graph,
  author = {Viet Dac Lai and Minh Van Nguyen and Thien Huu Nguyen and Franck Dernoncourt},
  title = {{Graph Learning Regularization and Transfer Learning for Few-Shot Event Detection}},
  booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year = {2021},
  doi = {10.1145/3404835.3463054},
}

Loading related content...

Figure