@inproceedings{ccdea620421f4a5dbb6a35796f885df4,
title = "Enhancing Variational Autoencoders with Mutual Information Neural Estimation for Text Generation",
abstract = "While broadly applicable to many natural language processing (NLP) tasks, variational autoencoders (VAEs) are hard to train due to the posterior collapse issue where the latent variable fails to encode the input data effectively. Various approaches have been proposed to alleviate this problem to improve the capability of the VAE. In this paper, we propose to introduce a mutual information (MI) term between the input and its latent variable to regularize the objective of the VAE. Since estimating the MI in the high-dimensional space is intractable, we employ neural networks for the estimation of the MI and provide a training algorithm based on the convex duality approach. Our experimental results on three benchmark datasets demonstrate that the proposed model, compared to the state-of-the-art baselines, exhibits less posterior collapse and has comparable or better performance in language modeling and text generation. We also qualitatively evaluate the inferred latent space and show that the proposed model can generate more reasonable and diverse sentences via linear interpolation in the latent space.",
author = "Dong Qian and Cheung, {Kwok Wai}",
note = "Publisher copyright: {\textcopyright} 2019 Association for Computational Linguistics; 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 ; Conference date: 03-11-2019 Through 07-11-2019",
year = "2019",
month = nov,
doi = "10.18653/v1/D19-1416",
language = "English",
series = "EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "4047--4057",
editor = "Kentaro Inui and Jing Jiang and Vincent Ng and Xiaojun Wan",
booktitle = "EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference",
address = "United States",
}