Document-level Relation Extraction with Progressive Self-distillation

Author:

Wang Quan1ORCID,Mao ZhendongORCID,Gao JieORCID,Zhang YongdongORCID

Affiliation:

1. MOE Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Beijing, China

Abstract

Document-level relation extraction (RE) aims to simultaneously predict relations (including no-relation cases denoted as NA) between all entity pairs in a document. It is typically formulated as a relation classification task with entities pre-detected in advance and solved by a hard-label training regime, which, however, neglects the divergence of the NA class and the correlations among other classes. This article introduces progressive self-distillation (PSD), a new training regime that employs online, self-knowledge distillation (KD) to produce and incorporate soft labels for document-level RE.The key idea of PSD is to gradually soften hard labels using past predictions from an RE model itself, which are adjusted adaptively as training proceeds. As such, PSD has to learn only one RE model within a single training pass, requiring no extra computation or annotation to pretrain another high-capacity teacher. PSD is conceptually simple, easy to implement, and generally applicable to various RE models to further improve their performance, without introducing additional parameters or significantly increasing training overheads into the models. It is also a general framework that can be flexibly extended to distilling various types of knowledge, rather than being restricted to soft labels themselves. Extensive experiments on four benchmarking datasets verify the effectiveness and generality of the proposed approach. The code is available at https://github.com/GaoJieCN/psd

Funder

National Natural Science Foundation of China

Publisher

Association for Computing Machinery (ACM)

Reference80 articles.

1. Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E. Dahl, and Geoffrey E. Hinton. 2018. Large scale distributed neural network training through online distillation. In Proceedings of the International Conference on Learning Representations. Retrieved from https://arxiv.org/abs/1804.03235

2. Jimmy Ba and Rich Caruana. 2014. Do deep nets really need to be deep? In Advances in Neural Information Processing Systems, Vol. 27. Retrieved from https://proceedings.neurips.cc/paper/2014/file/ea8fcd92d59581717e06eb187f10666d-Paper.pdf

3. Matching the Blanks: Distributional Similarity for Relation Learning

4. SciBERT: A Pretrained Language Model for Scientific Text

5. Bidirectional Recurrent Convolutional Neural Network for Relation Classification

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3