Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation
This work improves sentiment analysis for specific aspects in text, representing an incremental advance in domain-specific NLP.
The paper tackled the problem of aspect-based sentiment analysis by addressing limitations in prior graph-based models that ignored aspect terms and contextual importance scores from dependency trees, resulting in state-of-the-art performance on three benchmark datasets.
Aspect-based Sentiment Analysis (ABSA) seeks to predict the sentiment polarity of a sentence toward a specific aspect. Recently, it has been shown that dependency trees can be integrated into deep learning models to produce the state-of-the-art performance for ABSA. However, these models tend to compute the hidden/representation vectors without considering the aspect terms and fail to benefit from the overall contextual importance scores of the words that can be obtained from the dependency tree for ABSA. In this work, we propose a novel graph-based deep learning model to overcome these two issues of the prior work on ABSA. In our model, gate vectors are generated from the representation vectors of the aspect terms to customize the hidden vectors of the graph-based models toward the aspect terms. In addition, we propose a mechanism to obtain the importance scores for each word in the sentences based on the dependency trees that are then injected into the model to improve the representation vectors for ABSA. The proposed model achieves the state-of-the-art performance on three benchmark datasets.