@inproceedings{olabiyi-etal-2019-multi,
title = "Multi-turn Dialogue Response Generation in an Adversarial Learning Framework",
author = "Olabiyi, Oluwatobi and
Salimov, Alan O and
Khazane, Anish and
Mueller, Erik",
editor = "Chen, Yun-Nung and
Bedrax-Weiss, Tania and
Hakkani-Tur, Dilek and
Kumar, Anuj and
Lewis, Mike and
Luong, Thang-Minh and
Su, Pei-Hao and
Wen, Tsung-Hsien",
booktitle = "Proceedings of the First Workshop on NLP for Conversational AI",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4114",
doi = "10.18653/v1/W19-4114",
pages = "121--132",
abstract = "We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN{'}s generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirectional RNN that shares context and word embeddings with the generator. During inference, noise samples conditioned on the dialogue history are used to perturb the generator{'}s latent space to generate several possible responses. The final response is the one ranked best by the discriminator. The hredGAN shows improved performance over existing methods: (1) it generalizes better than networks trained using only the log-likelihood criterion, and (2) it generates longer, more informative and more diverse responses with high utterance and topic relevance even with limited training data. This performance improvement is demonstrated on the Movie triples and Ubuntu dialogue datasets with both the automatic and human evaluations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="olabiyi-etal-2019-multi">
<titleInfo>
<title>Multi-turn Dialogue Response Generation in an Adversarial Learning Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oluwatobi</namePart>
<namePart type="family">Olabiyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Salimov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anish</namePart>
<namePart type="family">Khazane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on NLP for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tania</namePart>
<namePart type="family">Bedrax-Weiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thang-Minh</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei-Hao</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN’s generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirectional RNN that shares context and word embeddings with the generator. During inference, noise samples conditioned on the dialogue history are used to perturb the generator’s latent space to generate several possible responses. The final response is the one ranked best by the discriminator. The hredGAN shows improved performance over existing methods: (1) it generalizes better than networks trained using only the log-likelihood criterion, and (2) it generates longer, more informative and more diverse responses with high utterance and topic relevance even with limited training data. This performance improvement is demonstrated on the Movie triples and Ubuntu dialogue datasets with both the automatic and human evaluations.</abstract>
<identifier type="citekey">olabiyi-etal-2019-multi</identifier>
<identifier type="doi">10.18653/v1/W19-4114</identifier>
<location>
<url>https://aclanthology.org/W19-4114</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>121</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-turn Dialogue Response Generation in an Adversarial Learning Framework
%A Olabiyi, Oluwatobi
%A Salimov, Alan O.
%A Khazane, Anish
%A Mueller, Erik
%Y Chen, Yun-Nung
%Y Bedrax-Weiss, Tania
%Y Hakkani-Tur, Dilek
%Y Kumar, Anuj
%Y Lewis, Mike
%Y Luong, Thang-Minh
%Y Su, Pei-Hao
%Y Wen, Tsung-Hsien
%S Proceedings of the First Workshop on NLP for Conversational AI
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F olabiyi-etal-2019-multi
%X We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN’s generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirectional RNN that shares context and word embeddings with the generator. During inference, noise samples conditioned on the dialogue history are used to perturb the generator’s latent space to generate several possible responses. The final response is the one ranked best by the discriminator. The hredGAN shows improved performance over existing methods: (1) it generalizes better than networks trained using only the log-likelihood criterion, and (2) it generates longer, more informative and more diverse responses with high utterance and topic relevance even with limited training data. This performance improvement is demonstrated on the Movie triples and Ubuntu dialogue datasets with both the automatic and human evaluations.
%R 10.18653/v1/W19-4114
%U https://aclanthology.org/W19-4114
%U https://doi.org/10.18653/v1/W19-4114
%P 121-132
Markdown (Informal)
[Multi-turn Dialogue Response Generation in an Adversarial Learning Framework](https://aclanthology.org/W19-4114) (Olabiyi et al., ACL 2019)
ACL