计算机工程与科学2024，Vol.46Issue(4)：716-724,9.DOI:10.3969/j.issn.1007-130X.2024.04.016
基于多视角对比学习的隐式篇章关系识别
Implicit discourse relation recognition with multi-view contrastive learning
摘要
Abstract
Previous researches on implicit discourse relationship recognition(IDRR)usually focus on designing effective discourse encoders.Different from theirs,this paper proposes a novel approach which introduces contrastive learning into IDRR so as to obtain representations of discourse units(DUs)with more differentiation.Specifically,a lightweight IDRR classification model is firstly adopted.Then,to better learn representations of DUs,the application of three different contrastive learning methods in IDDR are explored from multiple views,including instance-level,batch-level,and group-level.Finally,three multi-view contrastive learning objectives are combined for better IDRR.Our pro-posed method only slightly increases training time and introduces small additional parameters.Experi-mental results on PDTB 2.0 show that our method achieves the state-of-the-art performance.关键词
隐式篇章关系识别/多视角/对比学习/联合学习Key words
implicit discourse relation recognition/multi-view/contrastive learning/joint learning分类
信息技术与安全科学引用本文复制引用
吴一珩,李军辉,朱慕华..基于多视角对比学习的隐式篇章关系识别[J].计算机工程与科学,2024,46(4):716-724,9.基金项目
国家自然科学基金(61876120) （61876120）
