Left-Center-Right Separated Neural Network for Aspect-based Sentiment Analysis with Rotatory Attention

TL;DR

This paper introduces LCR-Rot, a neural network with rotatory attention and separated LSTMs for improved aspect-based sentiment analysis, effectively capturing target-context interactions and outperforming existing methods.

Contribution

The paper proposes a novel LCR-Rot model with separated LSTMs and rotatory attention to better represent multi-word targets and model target-context interactions.

Findings

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

Effectively captures important sentiment words in context and target.

Demonstrates the effectiveness of rotatory attention mechanism.

Abstract

Deep learning techniques have achieved success in aspect-based sentiment analysis in recent years. However, there are two important issues that still remain to be further studied, i.e., 1) how to efficiently represent the target especially when the target contains multiple words; 2) how to utilize the interaction between target and left/right contexts to capture the most important words in them. In this paper, we propose an approach, called left-center-right separated neural network with rotatory attention (LCR-Rot), to better address the two problems. Our approach has two characteristics: 1) it has three separated LSTMs, i.e., left, center and right LSTMs, corresponding to three parts of a review (left context, target phrase and right context); 2) it has a rotatory attention mechanism which models the relation between target and left/right contexts. The target2context attention is used to capture the most indicative sentiment words in left/right contexts. Subsequently, the context2target attention is used to capture the most important word in the target. This leads to a two-side representation of the target: left-aware target and right-aware target. We compare our approach on three benchmark datasets with ten related methods proposed recently. The results show that our approach significantly outperforms the state-of-the-art techniques.