Embarrassingly Simple Unsupervised Aspect Based Sentiment Tuple Extraction

TL;DR

This paper introduces a straightforward unsupervised method for extracting aspect-based sentiment tuples, including opinion terms and polarity, from sentences, especially useful in low-resource domains where labeled data is scarce.

Contribution

It presents a novel unsupervised approach for aspect-based sentiment tuple extraction, filling a gap in opinion word mining and establishing a new benchmark.

Findings

Effective in low-resource domains

Achieves strong performance on benchmark datasets

Establishes a baseline for unsupervised opinion mining

Abstract

Aspect Based Sentiment Analysis (ABSA) tasks involve the extraction of fine-grained sentiment tuples from sentences, aiming to discern the author's opinions. Conventional methodologies predominantly rely on supervised approaches; however, the efficacy of such methods diminishes in low-resource domains lacking labeled datasets since they often lack the ability to generalize across domains. To address this challenge, we propose a simple and novel unsupervised approach to extract opinion terms and the corresponding sentiment polarity for aspect terms in a sentence. Our experimental evaluations, conducted on four benchmark datasets, demonstrate compelling performance to extract the aspect oriented opinion words as well as assigning sentiment polarity. Additionally, unsupervised approaches for opinion word mining have not been explored and our work establishes a benchmark for the same.