Combining Convolution and Recursive Neural Networks for Sentiment Analysis
Abstract
This paper addresses the problem of sentence-level sentiment analysis. In recent years, Convolution and Recursive Neural Networks have been proven to be effective network architecture for sentence-level sentiment analysis. Nevertheless, each of them has their own potential drawbacks. For alleviating their weaknesses, we combined Convolution and Recursive Neural Networks into a new network architecture. In addition, we employed transfer learning from a large document-level labeled sentiment dataset to improve the word embedding in our models. The resulting models outperform all recent Convolution and Recursive Neural Networks. Beyond that, our models achieve comparable performance with state-of-the-art systems on Stanford Sentiment Treebank.
Cite
@article{arxiv.1801.09053,
title = {Combining Convolution and Recursive Neural Networks for Sentiment Analysis},
author = {Vinh D. Van and Thien Thai and Minh-Quoc Nghiem},
journal= {arXiv preprint arXiv:1801.09053},
year = {2018}
}
Comments
8 pages, 3 figures, Proceedings of the Eighth International Symposium on Information and Communication Technology. ACM, 2017