Meta-learning based instance manipulation for implicit discourse relation recognition

Without discourse connectives, implicit discourse relations recognition (IDRR) remains a challenging task and has attracted increasing attention. However, most studies ignore the issues of class imbalance and data noise. To alleviate these two problems, in this paper, we propose to improve the robus...

Full description

Saved in:
Bibliographic Details
Published inKnowledge-based systems Vol. 267; p. 110457
Main Authors Zeng, Jiali, Xie, Binbin, Wu, Changxing, Yin, Yongjing, Zeng, Hualin, Su, Jinsong
Format Journal Article
LanguageEnglish
Published Elsevier B.V 12.05.2023
Subjects
Class imbalance
Implicit discourse relation recognition
Instance weight
Meta learning
Class imbalance
Instance weight
Implicit discourse relation recognition
Meta learning
Online AccessGet full text

Cover

More Information
Summary:Without discourse connectives, implicit discourse relations recognition (IDRR) remains a challenging task and has attracted increasing attention. However, most studies ignore the issues of class imbalance and data noise. To alleviate these two problems, in this paper, we propose to improve the robustness of IDRR models with two novel meta-learning based instance manipulation networks: Meta-Weight-Net (MW-Net) and Meta-Label-Net (ML-Net), which adaptively control the effect of training instances and smooth the label distributions during model training, respectively. Specifically, we use MW-Net to adaptively learn an instance weight function directly from data and integrates the instance weights into the objective function of IDRR. Meanwhile, we adopt ML-Net to dynamically refine the label distributions, leading to the smaller variance in updating gradients. We conduct experiments on the PDTB 2.0 corpus. Experimental results and in-depth analysis empirically demonstrate the effectiveness of our networks.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2023.110457