Improving BERT Performance for Aspect-Based Sentiment Analysis
This work addresses the problem of enhancing sentiment analysis accuracy for product reviews, which is incremental as it builds on existing BERT methods with new modules.
The paper tackled improving BERT's performance for Aspect-Based Sentiment Analysis (ABSA) by proposing Parallel Aggregation and Hierarchical Aggregation modules, which eliminated the need for further BERT training and enhanced results for Aspect Extraction and Aspect Sentiment Classification tasks.
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.