Improved Memory Network for Aspect Sentiment Analysis
Abstract
In order to explore impact of different memory modules under the framework of deep memory network for aspect level sentiment classification, three kinds of different memory modules are designed. One of them uses CNN to build a memory module, which is capable of capturing local information from original sentence. The other one of them uses BiLSTM to build another memory module, which is capable of capturing sequence information. And the last one of them uses CNN and BiLSTM, which combines both local and sequence information together, to build memory module at the same time. Experiments on laptop and restaurant datasets demonstrate that our three methods achieve better results than MemNet and feature based SVM approach.
Keywords
Sentiment analysis, Deep memory network, Convolutional neural networks, Bidirectional Long short term memory
DOI
10.12783/dtcse/cmsam2018/26549
10.12783/dtcse/cmsam2018/26549
Refbacks
- There are currently no refbacks.