Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model

16Citations
Citations of this article
77Readers
Mendeley users who have this article in their library.

Abstract

Aspect-based sentiment analysis (ABSA) task consists of three typical subtasks: aspect term extraction, opinion term extraction, and sentiment polarity classification. These three subtasks are usually performed jointly to save resources and reduce the error propagation in the pipeline. However, most of the existing joint models only focus on the benefits of encoder sharing between subtasks but ignore the difference. Therefore, we propose a joint ABSA model, which not only enjoys the benefits of encoder sharing but also focuses on the difference to improve the effectiveness of the model. In detail, we introduce a dual-encoder design, in which a pair encoder especially focuses on candidate aspect-opinion pair classification, and the original encoder keeps attention on sequence labeling. Empirical results show that our proposed model shows robustness and significantly outperforms the previous state-of-the-art on four benchmark datasets.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Jing, H., Li, Z., Zhao, H., & Jiang, S. (2021). Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model. In EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 3910–3922). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.emnlp-main.318

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 17

77%

Researcher 3

14%

Professor / Associate Prof. 1

5%

Lecturer / Post doc 1

5%

Readers' Discipline

Tooltip

Computer Science 24

80%

Linguistics 4

13%

Neuroscience 1

3%

Social Sciences 1

3%

Save time finding and organizing research with Mendeley

Sign up for free