Please use this identifier to cite or link to this item:
Title: Soft labeling constraint for generalizing from sentiments in single domain
Authors: Roy, Abhinaba
Cambria, Erik
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: Roy, A. & Cambria, E. (2022). Soft labeling constraint for generalizing from sentiments in single domain. Knowledge-Based Systems, 245, 108346-.
Project: A18A2b0046
Journal: Knowledge-Based Systems
Abstract: In this work, we deal with domain generalization in sentiment analysis. In traditional domain generalization systems, multiple source domains are used to generalize to a single target domain. However, we tackle the scenario where examples of sentiments from only one domain are available. Recent works have proposed to generate target domain examples from a single source domain by means of an adversarial training, ensuring that generated examples performs well on classifier trained on source domain. However, the inherent assumption is that domain shift is only due to covariate shift. In our work, we argue that, in realistic scenarios such as sentiment analysis, there is significant change in label distribution across domains as well. Subsequently, we propose a soft labeling formulation that provides better generalization and more robust classifiers across unseen sentiment domains. Experimental results on the Amazon-reviews benchmark dataset show the effectiveness of the proposed formulation.
ISSN: 0950-7051
DOI: 10.1016/j.knosys.2022.108346
Rights: © 2022 Published by Elsevier B.V. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 50

Updated on Nov 25, 2022

Web of ScienceTM
Citations 50

Updated on Nov 24, 2022

Page view(s)

Updated on Nov 30, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.