@inproceedings{wang-wan-2020-adversarial,
title = "Adversarial Text Generation via Sequence Contrast Discrimination",
author = "Wang, Ke and
Wan, Xiaojun",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.5/",
doi = "10.18653/v1/2020.findings-emnlp.5",
pages = "47--53",
abstract = "In this paper, we propose a sequence contrast loss driven text generation framework, which learns the difference between real texts and generated texts and uses that difference. Specifically, our discriminator contains a discriminative sequence generator instead of a binary classifier, and measures the {\textquoteleft}relative realism' of generated texts against real texts by making use of them simultaneously. Moreover, our generator uses discriminative sequences to directly improve itself, which not only replaces the gradient propagation process from the discriminator to the generator, but also avoids the time-consuming sampling process of estimating rewards in some previous methods. We conduct extensive experiments with various metrics, substantiating that our framework brings improvements in terms of training stability and the quality of generated texts."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-wan-2020-adversarial">
<titleInfo>
<title>Adversarial Text Generation via Sequence Contrast Discrimination</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose a sequence contrast loss driven text generation framework, which learns the difference between real texts and generated texts and uses that difference. Specifically, our discriminator contains a discriminative sequence generator instead of a binary classifier, and measures the ‘relative realism’ of generated texts against real texts by making use of them simultaneously. Moreover, our generator uses discriminative sequences to directly improve itself, which not only replaces the gradient propagation process from the discriminator to the generator, but also avoids the time-consuming sampling process of estimating rewards in some previous methods. We conduct extensive experiments with various metrics, substantiating that our framework brings improvements in terms of training stability and the quality of generated texts.</abstract>
<identifier type="citekey">wang-wan-2020-adversarial</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.5</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.5/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>47</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarial Text Generation via Sequence Contrast Discrimination
%A Wang, Ke
%A Wan, Xiaojun
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wang-wan-2020-adversarial
%X In this paper, we propose a sequence contrast loss driven text generation framework, which learns the difference between real texts and generated texts and uses that difference. Specifically, our discriminator contains a discriminative sequence generator instead of a binary classifier, and measures the ‘relative realism’ of generated texts against real texts by making use of them simultaneously. Moreover, our generator uses discriminative sequences to directly improve itself, which not only replaces the gradient propagation process from the discriminator to the generator, but also avoids the time-consuming sampling process of estimating rewards in some previous methods. We conduct extensive experiments with various metrics, substantiating that our framework brings improvements in terms of training stability and the quality of generated texts.
%R 10.18653/v1/2020.findings-emnlp.5
%U https://aclanthology.org/2020.findings-emnlp.5/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.5
%P 47-53
Markdown (Informal)
[Adversarial Text Generation via Sequence Contrast Discrimination](https://aclanthology.org/2020.findings-emnlp.5/) (Wang & Wan, Findings 2020)
ACL