Aspect Level Sentiment Classification with Deep Memory Network

We introduce a deep memory network for aspect level sentiment classification. Unlike feature-based SVM and sequential neural models such as LSTM, this approach explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect. Such importance degree and text representation are calculated with multiple computational layers, each of which is a neural attention model over an external memory. Experiments on laptop and restaurant datasets demonstrate that our approach performs comparable to state-of-art feature based SVM system, and substantially better than LSTM and attention-based LSTM architectures. On both datasets we show that multiple computational layers could improve…

• NN
  National Natural Science Foundation of China

  Awards: 61273321, 61632011, 863 Program, No. 61632011, 2015AA015407
• NH
  National High-tech Research and Development Program