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

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-ofthe-art on four benchmark datasets.

A Joint Learning Model for Aspect-based Sentiment Analysis via Machine Reading Comprehension and Graph Convolutional Network

“…The collapsed method [3][4][5] ignores the boundary of two tasks and adopts a unified labeling scheme to represent each token. Another type of method [6][7][8][9][10] utilizes the relationship between tasks by jointly training two subtasks within the framework of multitasking learning.…”