ASTE Transformer Modelling Dependencies in Aspect-Sentiment Triplet Extraction

TL;DR

This paper introduces a transformer-based model for aspect-sentiment triplet extraction that models dependencies between phrases and classifier decisions, outperforming previous methods on benchmark datasets.

Contribution

The paper proposes a novel transformer-inspired architecture for ASTE that captures dependencies between phrases and classifier outputs, enhancing extraction performance.

Findings

Achieves higher F1 scores than existing methods on benchmark datasets.

Pre-training further improves model performance.

Models dependencies between phrases and classifier decisions effectively.

Abstract

Aspect-Sentiment Triplet Extraction (ASTE) is a recently proposed task of aspect-based sentiment analysis that consists in extracting (aspect phrase, opinion phrase, sentiment polarity) triples from a given sentence. Recent state-of-the-art methods approach this task by first extracting all possible text spans from a given text, then filtering the potential aspect and opinion phrases with a classifier, and finally considering all their pairs with another classifier that additionally assigns sentiment polarity to them. Although several variations of the above scheme have been proposed, the common feature is that the final result is constructed by a sequence of independent classifier decisions. This hinders the exploitation of dependencies between extracted phrases and prevents the use of knowledge about the interrelationships between classifier predictions to improve performance. In this paper, we propose a new ASTE approach consisting of three transformer-inspired layers, which enables the modelling of dependencies both between phrases and between the final classifier decisions. Experimental results show that the method achieves higher performance in terms of F1 measure than other methods studied on popular benchmarks. In addition, we show that a simple pre-training technique further improves the performance of the model.