Convolution-based Memory Network for Aspect-based Sentiment Analysis

Chuang Fan, Qinghong Gao, Jiachen Du, Lin Gui, Ruifeng Xu, Kam-Fai Wong

Abstract: Memory networks have shown expressive performance on aspect based sentiment analysis. However, ordinary memory networks only capture word-level information and lack the capacity for modeling complicated expressions which consist of multiple words. Targeting this problem, we propose a novel convolutional memory network which incorporates an attention mechanism. This model sequentially computes the weights of multiple memory units corresponding to multi-words. This model may capture both words and multi-words expressions in sentences for aspect-based sentiment analysis. Experimental results show that the proposed model outperforms the state-of-the-art baselines.