Paper: Hybrid Deep Belief Networks for Semi-supervised Sentiment Classification

ACL ID C14-1127
Title Hybrid Deep Belief Networks for Semi-supervised Sentiment Classification
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2014
Authors

In this paper, we develop a novel semi-supervised learning algorithm called hybrid deep be- lief networks (HDBN), to address the semi-supervised sentiment classification problem with deep learning. First, we construct the previous several hidden layers using restricted Boltzmann machines (RBM), which can reduce the dimension and abstract the information of the reviews quickly. Second, we construct the following hidden layers using convolutional restricted Boltz- mann machines (CRBM), which can abstract the information of reviews effectively. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. We did several experiments on five sentiment classification datasets, and show that HDBN is competitive with previou...