Attention Based LSTM for Target Dependent Sentiment Classification
DOI:
https://doi.org/10.1609/aaai.v31i1.11061Keywords:
sentiment classification, LSTMAbstract
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.
Downloads
Published
2017-02-12
How to Cite
Yang, M., Tu, W., Wang, J., Xu, F., & Chen, X. (2017). Attention Based LSTM for Target Dependent Sentiment Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.11061
Issue
Section
Student Abstract Track