Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network

TL;DR

This paper introduces CAPSAR, a capsule network model that improves aspect-term sentiment analysis by discovering potential aspect terms without prior aspect annotations, outperforming existing methods.

Contribution

The novel CAPSAR model leverages capsule networks and sentiment-aspect reconstruction to identify aspect terms in sentiment analysis without explicit aspect annotations.

Findings

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

The model effectively discovers aspect terms from sentences without prior annotations.

Experiments demonstrate the coherence of aspect-sentiment patterns captured by capsules.

Abstract

Most recent existing aspect-term level sentiment analysis (ATSA) approaches combined various neural network models with delicately carved attention mechanisms built upon given aspect and context to generate refined sentence representations for better predictions. In these methods, aspect terms are always provided in both training and testing process which may degrade aspect-level analysis into sentence-level prediction. However, the annotated aspect term might be unavailable in real-world scenarios which may challenge the applicability of the existing methods. In this paper, we aim to improve ATSA by discovering the potential aspect terms of the predicted sentiment polarity when the aspect terms of a test sentence are unknown. We access this goal by proposing a capsule network based model named CAPSAR. In CAPSAR, sentiment categories are denoted by capsules and aspect term information is injected into sentiment capsules through a sentiment-aspect reconstruction procedure during the training. As a result, coherent patterns between aspects and sentimental expressions are encapsulated by these sentiment capsules. Experiments on three widely used benchmarks demonstrate these patterns have potential in exploring aspect terms from test sentence when only feeding the sentence to the model. Meanwhile, the proposed CAPSAR can clearly outperform SOTA methods in standard ATSA tasks.