Aspect-based Sentiment Analysis through EDU-level Attentions

TL;DR

This paper introduces an EDU-level attention mechanism for aspect-based sentiment analysis, improving accuracy by focusing on discourse units and leveraging automatic EDU segmentation.

Contribution

It proposes a novel EDU-aware attention model that enhances sentiment analysis by explicitly modeling discourse units and does not require manual EDU boundary annotation.

Findings

Outperforms state-of-the-art baselines on benchmark datasets

Utilizes automatic EDU segmentation for practical application

Enhances aspect-specific sentiment detection accuracy

Abstract

A sentence may express sentiments on multiple aspects. When these aspects are associated with different sentiment polarities, a model's accuracy is often adversely affected. We observe that multiple aspects in such hard sentences are mostly expressed through multiple clauses, or formally known as elementary discourse units (EDUs), and one EDU tends to express a single aspect with unitary sentiment towards that aspect. In this paper, we propose to consider EDU boundaries in sentence modeling, with attentions at both word and EDU levels. Specifically, we highlight sentiment-bearing words in EDU through word-level sparse attention. Then at EDU level, we force the model to attend to the right EDU for the right aspect, by using EDU-level sparse attention and orthogonal regularization. Experiments on three benchmark datasets show that our simple EDU-Attention model outperforms state-of-the-art baselines. Because EDU can be automatically segmented with high accuracy, our model can be applied to sentences directly without the need of manual EDU boundary annotation.