@inproceedings{ke-etal-2019-araml,
title = "{ARAML}: A Stable Adversarial Training Framework for Text Generation",
author = "Ke, Pei and
Huang, Fei and
Huang, Minlie and
Zhu, Xiaoyan",
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/D19-1436",
doi = "10.18653/v1/D19-1436",
pages = "4271--4281",
abstract = "Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we propose a novel framework called Adversarial Reward Augmented Maximum Likelihood (ARAML). During adversarial training, the discriminator assigns rewards to samples which are acquired from a stationary distribution near the data rather than the generator{'}s distribution. The generator is optimized with maximum likelihood estimation augmented by the discriminator{'}s rewards instead of policy gradient. Experiments show that our model can outperform state-of-the-art text GANs with a more stable training process.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ke-etal-2019-araml">
<titleInfo>
<title>ARAML: A Stable Adversarial Training Framework for Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Ke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minlie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyan</namePart>
<namePart type="family">Zhu</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>Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we propose a novel framework called Adversarial Reward Augmented Maximum Likelihood (ARAML). During adversarial training, the discriminator assigns rewards to samples which are acquired from a stationary distribution near the data rather than the generator’s distribution. The generator is optimized with maximum likelihood estimation augmented by the discriminator’s rewards instead of policy gradient. Experiments show that our model can outperform state-of-the-art text GANs with a more stable training process.</abstract>
<identifier type="citekey">ke-etal-2019-araml</identifier>
<identifier type="doi">10.18653/v1/D19-1436</identifier>
<location>
<url>https://aclanthology.org/D19-1436</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>4271</start>
<end>4281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ARAML: A Stable Adversarial Training Framework for Text Generation
%A Ke, Pei
%A Huang, Fei
%A Huang, Minlie
%A Zhu, Xiaoyan
%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 ke-etal-2019-araml
%X Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we propose a novel framework called Adversarial Reward Augmented Maximum Likelihood (ARAML). During adversarial training, the discriminator assigns rewards to samples which are acquired from a stationary distribution near the data rather than the generator’s distribution. The generator is optimized with maximum likelihood estimation augmented by the discriminator’s rewards instead of policy gradient. Experiments show that our model can outperform state-of-the-art text GANs with a more stable training process.
%R 10.18653/v1/D19-1436
%U https://aclanthology.org/D19-1436
%U https://doi.org/10.18653/v1/D19-1436
%P 4271-4281
Markdown (Informal)
[ARAML: A Stable Adversarial Training Framework for Text Generation](https://aclanthology.org/D19-1436) (Ke et al., EMNLP-IJCNLP 2019)
ACL
- Pei Ke, Fei Huang, Minlie Huang, and Xiaoyan Zhu. 2019. ARAML: A Stable Adversarial Training Framework for Text Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4271–4281, Hong Kong, China. Association for Computational Linguistics.