A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis

TL;DR

This paper introduces a unified end-to-end framework for aspect-based sentiment analysis that jointly extracts aspect terms, opinion terms, and sentiment polarity triples using shared BERT-based MRC models, outperforming existing methods.

Contribution

It proposes a novel joint training approach with shared parameters for multiple subtasks in ABSA, enabling comprehensive triple extraction in a unified framework.

Findings

Significantly outperforms state-of-the-art methods on benchmark datasets.

Effectively extracts aspect, opinion, and sentiment triples simultaneously.

Demonstrates the advantages of joint training with shared BERT-MRC models.

Abstract

Aspect based sentiment analysis (ABSA) involves three fundamental subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Early works only focused on solving one of these subtasks individually. Some recent work focused on solving a combination of two subtasks, e.g., extracting aspect terms along with sentiment polarities or extracting the aspect and opinion terms pair-wisely. More recently, the triple extraction task has been proposed, i.e., extracting the (aspect term, opinion term, sentiment polarity) triples from a sentence. However, previous approaches fail to solve all subtasks in a unified end-to-end framework. In this paper, we propose a complete solution for ABSA. We construct two machine reading comprehension (MRC) problems and solve all subtasks by joint training two BERT-MRC models with parameters sharing. We conduct experiments on these subtasks, and results on several benchmark datasets demonstrate the effectiveness of our proposed framework, which significantly outperforms existing state-of-the-art methods.