Improving BERT Performance for Aspect-Based Sentiment Analysis

TL;DR

This paper introduces two modules, Parallel and Hierarchical Aggregation, to enhance BERT's performance on Aspect-Based Sentiment Analysis tasks without additional BERT training.

Contribution

The paper proposes simple aggregation modules that improve BERT-based ABSA performance and eliminate the need for further BERT fine-tuning.

Findings

Improved accuracy on ABSA tasks with the proposed modules.

Modules do not require additional training of BERT.

Source code is publicly available for reproducibility.

Abstract

Aspect-Based Sentiment Analysis (ABSA) studies the consumer opinion on the market products. It involves examining the type of sentiments as well as sentiment targets expressed in product reviews. Analyzing the language used in a review is a difficult task that requires a deep understanding of the language. In recent years, deep language models, such as BERT \cite{devlin2019bert}, have shown great progress in this regard. In this work, we propose two simple modules called Parallel Aggregation and Hierarchical Aggregation to be utilized on top of BERT for two main ABSA tasks namely Aspect Extraction (AE) and Aspect Sentiment Classification (ASC) in order to improve the model's performance. We show that applying the proposed models eliminates the need for further training of the BERT model. The source code is available on the Web for further research and reproduction of the results.