Aspect Based Sentiment Analysis with Gated Convolutional Networks

TL;DR

This paper introduces a convolutional neural network model with gating mechanisms for aspect-based sentiment analysis, achieving higher accuracy and efficiency than traditional LSTM and attention-based models.

Contribution

The paper presents a novel Gated Tanh-ReLU Units model that simplifies architecture and enhances parallelization for aspect-based sentiment analysis tasks.

Findings

Outperforms existing models on SemEval datasets

Achieves higher accuracy with reduced training time

Enables efficient parallel training due to convolutional architecture

Abstract

Aspect based sentiment analysis (ABSA) can provide more detailed information than general sentiment analysis, because it aims to predict the sentiment polarities of the given aspects or entities in text. We summarize previous approaches into two subtasks: aspect-category sentiment analysis (ACSA) and aspect-term sentiment analysis (ATSA). Most previous approaches employ long short-term memory and attention mechanisms to predict the sentiment polarity of the concerned targets, which are often complicated and need more training time. We propose a model based on convolutional neural networks and gating mechanisms, which is more accurate and efficient. First, the novel Gated Tanh-ReLU Units can selectively output the sentiment features according to the given aspect or entity. The architecture is much simpler than attention layer used in the existing models. Second, the computations of our model could be easily parallelized during training, because convolutional layers do not have time dependency as in LSTM layers, and gating units also work independently. The experiments on SemEval datasets demonstrate the efficiency and effectiveness of our models.