@inproceedings{li-etal-2017-adversarial,
title = "Adversarial Learning for Neural Dialogue Generation",
author = "Li, Jiwei and
Monroe, Will and
Shi, Tianlin and
Jean, S{\'e}bastien and
Ritter, Alan and
Jurafsky, Dan",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1230",
doi = "10.18653/v1/D17-1230",
pages = "2157--2169",
abstract = "We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem where we jointly train two systems: a generative model to produce response sequences, and a discriminator{---}analagous to the human evaluator in the Turing test{---} to distinguish between the human-generated dialogues and the machine-generated ones. In this generative adversarial network approach, the outputs from the discriminator are used to encourage the system towards more human-like dialogue. Further, we investigate models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2017-adversarial">
<titleInfo>
<title>Adversarial Learning for Neural Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiwei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Will</namePart>
<namePart type="family">Monroe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianlin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sébastien</namePart>
<namePart type="family">Jean</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem where we jointly train two systems: a generative model to produce response sequences, and a discriminator—analagous to the human evaluator in the Turing test— to distinguish between the human-generated dialogues and the machine-generated ones. In this generative adversarial network approach, the outputs from the discriminator are used to encourage the system towards more human-like dialogue. Further, we investigate models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines</abstract>
<identifier type="citekey">li-etal-2017-adversarial</identifier>
<identifier type="doi">10.18653/v1/D17-1230</identifier>
<location>
<url>https://aclanthology.org/D17-1230</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>2157</start>
<end>2169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarial Learning for Neural Dialogue Generation
%A Li, Jiwei
%A Monroe, Will
%A Shi, Tianlin
%A Jean, Sébastien
%A Ritter, Alan
%A Jurafsky, Dan
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F li-etal-2017-adversarial
%X We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem where we jointly train two systems: a generative model to produce response sequences, and a discriminator—analagous to the human evaluator in the Turing test— to distinguish between the human-generated dialogues and the machine-generated ones. In this generative adversarial network approach, the outputs from the discriminator are used to encourage the system towards more human-like dialogue. Further, we investigate models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines
%R 10.18653/v1/D17-1230
%U https://aclanthology.org/D17-1230
%U https://doi.org/10.18653/v1/D17-1230
%P 2157-2169
Markdown (Informal)
[Adversarial Learning for Neural Dialogue Generation](https://aclanthology.org/D17-1230) (Li et al., EMNLP 2017)
ACL
- Jiwei Li, Will Monroe, Tianlin Shi, Sébastien Jean, Alan Ritter, and Dan Jurafsky. 2017. Adversarial Learning for Neural Dialogue Generation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2157–2169, Copenhagen, Denmark. Association for Computational Linguistics.