Sentiment Lexicon Enhanced Attention-Based LSTM for Sentiment Classification
Abstract
Deep neural networks have gained great success recently for sentiment classification. However, these approaches do not fully exploit the linguistic knowledge. In this paper, we propose a novel sentiment lexicon enhanced attention-based LSTM (SLEA-LSTM) model to improve the performance of sentence-level sentiment classification. Our method successfully integrates sentiment lexicon into deep neural networks via single-head or multi-head attention mechanisms. We conduct extensive experiments on MR and SST datasets. The experimental results show that our model achieved comparable or better performance than the state-of-the-art methods.
Cite
Text
Lei et al. "Sentiment Lexicon Enhanced Attention-Based LSTM for Sentiment Classification." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12142Markdown
[Lei et al. "Sentiment Lexicon Enhanced Attention-Based LSTM for Sentiment Classification." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/lei2018aaai-sentiment/) doi:10.1609/AAAI.V32I1.12142BibTeX
@inproceedings{lei2018aaai-sentiment,
title = {{Sentiment Lexicon Enhanced Attention-Based LSTM for Sentiment Classification}},
author = {Lei, Zeyang and Yang, Yujiu and Yang, Min},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2018},
pages = {8105-8106},
doi = {10.1609/AAAI.V32I1.12142},
url = {https://mlanthology.org/aaai/2018/lei2018aaai-sentiment/}
}