Learn to Select via Hierarchical Gate Mechanism for Aspect-Based Sentiment
Analysis
Abstract
Aspect-based sentiment analysis (ABSA) is a finegrained task. Recurrent Neural Network (RNN)
model armed with attention mechanism seems a
natural fit for this task, and achieves the stateof-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 stateof-the-art baselines.