Learn to select via hierarchical gate mechanism for aspect-based sentiment analysis

Abstract

Aspect-based sentiment analysis (ABSA) is a fine-grained task. Recurrent Neural Network (RNN) model armed with attention mechanism seems a natural fit for this task, and achieves the state-of-the-art performance recently. However, previous attention mechanisms proposed for ABSA may attend irrelevant words and thus ruin the performance, especially when dealing with long and complex sentences with multiple aspects. In this paper, we propose a novel architecture named Hierarchical Gate Memory Network (HGMN) for ABSA: firstly, we employ the proposed hierarchical gate mechanism to learn to select the related part about the given aspect, which can keep the original sequence structure of sentence at the same time. After that, we apply Convolutional Neural Network (CNN) on the final aspect-specific memory. We conduct extensive experiments on the SemEval 2014 and Twitter dataset, and results demonstrate that our model outperforms attention based state-of-the-art baselines.