arXiv Analytics

Sign in

arXiv:2104.07650 [cs.CL]AbstractReferencesReviewsResources

AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction

Xiang Chen, Xin Xie, Ningyu Zhang, Jiahuan Yan, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

Published 2021-04-15Version 1

In this paper, we reformulate the relation extraction task as mask language modeling and propose a novel adaptive prompt-based finetuning approach. We propose an adaptive label words selection mechanism that scatters the relation label into variable number of label tokens to handle the complex multiple label space. We further introduce an auxiliary entity discriminator object to encourage the model to focus on context representation learning. Extensive experiments on benchmark datasets demonstrate that our approach can achieve better performance on both the few-shot and supervised setting.

Related articles: Most relevant | Search more
arXiv:2306.02051 [cs.CL] (Published 2023-06-03)
A Comprehensive Survey on Deep Learning for Relation Extraction: Recent Advances and New Frontiers
Zhao Xiaoyan et al.
arXiv:2206.07558 [cs.CL] (Published 2022-06-15)
Contextualization and Generalization in Entity and Relation Extraction
arXiv:1712.05191 [cs.CL] (Published 2017-12-14)
Relation Extraction : A Survey