OATS: Opinion Aspect Target Sentiment Quadruple Extraction Dataset for Aspect-Based Sentiment Analysis

TL;DR

The paper introduces OATS, a new dataset for aspect-based sentiment analysis that covers three new domains with detailed quadruple annotations, addressing limitations of existing datasets and enabling more comprehensive ABSA research.

Contribution

It provides a large, multi-domain dataset with sentence and review-level sentiment quadruples, facilitating advanced ABSA tasks and overcoming domain and granularity limitations of prior datasets.

Findings

Established baseline results for quadruple extraction tasks.

Demonstrated OATS's effectiveness across three new domains.

Highlighted the potential for improved ABSA models using OATS.

Abstract

Aspect-based sentiment analysis (ABSA) delves into understanding sentiments specific to distinct elements within a user-generated review. It aims to analyze user-generated reviews to determine a) the target entity being reviewed, b) the high-level aspect to which it belongs, c) the sentiment words used to express the opinion, and d) the sentiment expressed toward the targets and the aspects. While various benchmark datasets have fostered advancements in ABSA, they often come with domain limitations and data granularity challenges. Addressing these, we introduce the OATS dataset, which encompasses three fresh domains and consists of 27,470 sentence-level quadruples and 17,092 review-level tuples. Our initiative seeks to bridge specific observed gaps: the recurrent focus on familiar domains like restaurants and laptops, limited data for intricate quadruple extraction tasks, and an occasional oversight of the synergy between sentence and review-level sentiments. Moreover, to elucidate OATS's potential and shed light on various ABSA subtasks that OATS can solve, we conducted experiments, establishing initial baselines. We hope the OATS dataset augments current resources, paving the way for an encompassing exploration of ABSA (https://github.com/RiTUAL-UH/OATS-ABSA).