@inproceedings{xu-etal-2018-diversity,
title = "Diversity-Promoting {GAN}: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation",
author = "Xu, Jingjing and
Ren, Xuancheng and
Lin, Junyang and
Sun, Xu",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1428",
doi = "10.18653/v1/D18-1428",
pages = "3940--3949",
abstract = "Existing text generation methods tend to produce repeated and {''}boring{''} expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for {''}novel{''} and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2018-diversity">
<titleInfo>
<title>Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingjing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuancheng</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct"-"nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing text generation methods tend to produce repeated and ”boring” expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for ”novel” and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines.</abstract>
<identifier type="citekey">xu-etal-2018-diversity</identifier>
<identifier type="doi">10.18653/v1/D18-1428</identifier>
<location>
<url>https://aclanthology.org/D18-1428</url>
</location>
<part>
<date>2018-oct"-"nov</date>
<extent unit="page">
<start>3940</start>
<end>3949</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation
%A Xu, Jingjing
%A Ren, Xuancheng
%A Lin, Junyang
%A Sun, Xu
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct" "nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F xu-etal-2018-diversity
%X Existing text generation methods tend to produce repeated and ”boring” expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for ”novel” and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines.
%R 10.18653/v1/D18-1428
%U https://aclanthology.org/D18-1428
%U https://doi.org/10.18653/v1/D18-1428
%P 3940-3949
Markdown (Informal)
[Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation](https://aclanthology.org/D18-1428) (Xu et al., EMNLP 2018)
ACL