English

Dynamic Prefix-Tuning for Generative Template-based Event Extraction

Computation and Language 2022-12-19 v1 Artificial Intelligence

Abstract

We consider event extraction in a generative manner with template-based conditional generation. Although there is a rising trend of casting the task of event extraction as a sequence generation problem with prompts, these generation-based methods have two significant challenges, including using suboptimal prompts and static event type information. In this paper, we propose a generative template-based event extraction method with dynamic prefix (GTEE-DynPref) by integrating context information with type-specific prefixes to learn a context-specific prefix for each context. Experimental results show that our model achieves competitive results with the state-of-the-art classification-based model OneIE on ACE 2005 and achieves the best performances on ERE. Additionally, our model is proven to be portable to new types of events effectively.

Keywords

Cite

@article{arxiv.2205.06166,
  title  = {Dynamic Prefix-Tuning for Generative Template-based Event Extraction},
  author = {Xiao Liu and Heyan Huang and Ge Shi and Bo Wang},
  journal= {arXiv preprint arXiv:2205.06166},
  year   = {2022}
}

Comments

accepted by ACL 2022

R2 v1 2026-06-24T11:15:38.754Z