Learning to Ask for Data-Efficient Event Argument Extraction (Student Abstract)

Hongbin Ye, Ningyu Zhang, Zhen Bi, Shumin Deng, Chuanqi Tan, Hui Chen, Fei Huang, Huajun Chen

AAAI 2022 pp. 13099-13100

doi:10.1609/AAAI.V36I11.21686 /aaai/2022/ye2022aaai-learning/

Abstract

Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles. In this study, we cast EAE as a question-based cloze task and empirically analyze fixed discrete token template performance. As generating human-annotated question templates is often time-consuming and labor-intensive, we further propose a novel approach called “Learning to Ask,” which can learn optimized question templates for EAE without human annotations. Experiments using the ACE-2005 dataset demonstrate that our method based on optimized questions achieves state-of-the-art performance in both the few-shot and supervised settings.

PDF AAAI Semantic Scholar

Cite

Text

Ye et al. "Learning to Ask for Data-Efficient Event Argument Extraction (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21686

Markdown

[Ye et al. "Learning to Ask for Data-Efficient Event Argument Extraction (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/ye2022aaai-learning/) doi:10.1609/AAAI.V36I11.21686

BibTeX

@inproceedings{ye2022aaai-learning,
  title     = {{Learning to Ask for Data-Efficient Event Argument Extraction (Student Abstract)}},
  author    = {Ye, Hongbin and Zhang, Ningyu and Bi, Zhen and Deng, Shumin and Tan, Chuanqi and Chen, Hui and Huang, Fei and Chen, Huajun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {13099-13100},
  doi       = {10.1609/AAAI.V36I11.21686},
  url       = {https://mlanthology.org/aaai/2022/ye2022aaai-learning/}
}