Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification

TL;DR

This paper introduces AOAN, a novel neural network that improves aspect-based sentiment classification by better aligning opinion words with aspects, addressing semantic mismatches in multi-aspect sentences.

Contribution

The paper proposes a new Aspect-oriented Opinion Alignment Network with a neighboring span module and multi-perspective attention to enhance opinion-aspect alignment.

Findings

Achieves state-of-the-art results on three benchmark datasets.

Effectively manages semantic mismatches in multi-aspect sentences.

Outperforms previous attention-based models in opinion alignment.

Abstract

Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its context. Previous works have made remarkable progress in leveraging attention mechanism to extract opinion words for different aspects. However, a persistent challenge is the effective management of semantic mismatches, which stem from attention mechanisms that fall short in adequately aligning opinions words with their corresponding aspect in multi-aspect sentences. To address this issue, we propose a novel Aspect-oriented Opinion Alignment Network (AOAN) to capture the contextual association between opinion words and the corresponding aspect. Specifically, we first introduce a neighboring span enhanced module which highlights various compositions of neighboring words and given aspects. In addition, we design a multi-perspective attention mechanism that align relevant opinion information with respect to the given aspect. Extensive experiments on three benchmark datasets demonstrate that our model achieves state-of-the-art results. The source code is available at https://github.com/AONE-NLP/ABSA-AOAN.