Variational Autoencoder for Semi-Supervised Text Classification (original) (raw)

Authors

DOI:

https://doi.org/10.1609/aaai.v31i1.10966

Keywords:

variational autoencoder, semi-supervised learning, text classification

Abstract

Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the decoder's capability to distinguish between different categorical labels is essential. Therefore, Semi-supervised Sequential Variational Autoencoder (SSVAE) is proposed, which increases the capability by feeding label into its decoder RNN at each time-step. Two specific decoder structures are investigated and both of them are verified to be effective. Besides, in order to reduce the computational complexity in training, a novel optimization method is proposed, which estimates the gradient of the unlabeled objective function by sampling, along with two variance reduction techniques. Experimental results on Large Movie Review Dataset (IMDB) and AG's News corpus show that the proposed approach significantly improves the classification accuracy compared with pure-supervised classifiers, and achieves competitive performance against previous advanced methods. State-of-the-art results can be obtained by integrating other pretraining-based methods.

AAAI-2017 Proceedings Cover

How to Cite

Xu, W., Sun, H., Deng, C., & Tan, Y. (2017). Variational Autoencoder for Semi-Supervised Text Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.10966

Issue

Section

Main Track: NLP and Machine Learning