Improving BERT Performance for Aspect-Based Sentiment Analysis

Aspect-Based Sentiment Analysis (ABSA) addresses the problem of extracting sentiments and their targets from opinionated data such as consumer 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, 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). With the proposed modules, we show that the intermediate layers of the BERT architecture can be utilized for the enhancement of the model performance1