First Target and Opinion then Polarity: Enhancing Target-opinion Correlation for Aspect Sentiment Triplet Extraction

TL;DR

This paper introduces a two-stage framework for Aspect Sentiment Triplet Extraction that improves target-opinion correlation and reduces interference among triplets, leading to more accurate sentiment analysis.

Contribution

It proposes a novel method using artificial tags and attention restriction to enhance target-opinion correlation and triplet extraction accuracy.

Findings

Improved extraction accuracy on four datasets.

Effective enhancement of target-opinion correlation.

Reduced negative interference among sentiment triplets.

Abstract

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from a sentence, including target entities, associated sentiment polarities, and opinion spans which rationalize the polarities. Existing methods are short on building correlation between target-opinion pairs, and neglect the mutual interference among different sentiment triplets. To address these issues, we utilize a two-stage framework to enhance the correlation between targets and opinions: at stage one, we extract targets and opinions through sequence tagging; then we append a group of artificial tags named Perceivable Pair, which indicate the span of a specific target-opinion tuple, to the input sentence to obtain closer correlated target-opinion pair representation. Meanwhile, we reduce the negative interference between triplets by restricting tokens' attention field. Finally, the polarity is identified according to the representation of the Perceivable Pair. We conduct experiments on four datasets, and the experimental results show the effectiveness of our model.