Hybrid Deep Belief Networks for Semi-supervised Sentiment Classification

@inproceedings{Zhou2014HybridDB,
  title={Hybrid Deep Belief Networks for Semi-supervised Sentiment Classification},
  author={Shusen Zhou and Qingcai Chen and Xiaolong Wang and Xiaoling Li},
  booktitle={COLING},
  year={2014}
}
In this paper, we develop a novel semi-supervised learning algorithm called hybrid deep belief 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 Boltzmann machines (CRBM), which can… CONTINUE READING
8 Citations
20 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 20 references

Empirical evaluation of convolutional rbms for vision

  • Guillaume Desjardins, Yoshua Bengio.
  • Technical report.
  • 2008
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…