@inproceedings{qian-cheung-2019-enhancing,
title = "Enhancing Variational Autoencoders with Mutual Information Neural Estimation for Text Generation",
author = "Qian, Dong and
Cheung, William K.",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1416",
doi = "10.18653/v1/D19-1416",
pages = "4047--4057",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-cheung-2019-enhancing">
<titleInfo>
<title>Enhancing Variational Autoencoders with Mutual Information Neural Estimation for Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Cheung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">qian-cheung-2019-enhancing</identifier>
<identifier type="doi">10.18653/v1/D19-1416</identifier>
<location>
<url>https://aclanthology.org/D19-1416</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>4047</start>
<end>4057</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Variational Autoencoders with Mutual Information Neural Estimation for Text Generation
%A Qian, Dong
%A Cheung, William K.
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F qian-cheung-2019-enhancing
%X 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.
%R 10.18653/v1/D19-1416
%U https://aclanthology.org/D19-1416
%U https://doi.org/10.18653/v1/D19-1416
%P 4047-4057
Markdown (Informal)
[Enhancing Variational Autoencoders with Mutual Information Neural Estimation for Text Generation](https://aclanthology.org/D19-1416) (Qian & Cheung, EMNLP-IJCNLP 2019)
ACL