Attention Based LSTM for Target Dependent Sentiment Classification
Min Yang, Wenting Tu, Jingxuan Wang, Fei Xu, Xiaojun Chen · Proceedings of the AAAI Conference on Artificial Intelligence · 2017
We present an attention-based bidirectional LSTM approach to improve the target-dependent sentiment classification. Our method learns the alignment between the target entities and the most distinguishing features. We conduct extensive experiments on a real-life dataset. The experimental results show that our model achieves state-of-the-art results.