@inproceedings{chang-etal-2019-semi,
title = "A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation",
author = "Chang, Jinxin and
He, Ruifang and
Wang, Longbiao and
Zhao, Xiangyu and
Yang, Ting and
Wang, Ruifang",
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/D19-1200",
doi = "10.18653/v1/D19-1200",
pages = "1920--1930",
abstract = "Neural sequence-to-sequence models for dialog systems suffer from the problem of favoring uninformative and non replier-specific responses due to lack of the global and relevant information guidance. The existing methods model the generation process by leveraging the neural variational network with simple Gaussian. However, the sampled information from latent space usually becomes useless due to the KL divergence vanishing issue, and the highly abstractive global variables easily dilute the personal features of replier, leading to a non replier-specific response. Therefore, a novel Semi-Supervised Stable Variational Network (SSVN) is proposed to address these issues. We use a unit hypersperical distribution, namely the von Mises-Fisher (vMF), as the latent space of a semi-supervised model, which can obtain the stable KL performance by setting a fixed variance and hence enhance the global information representation. Meanwhile, an unsupervised extractor is introduced to automatically distill the replier-tailored feature which is then injected into a supervised generator to encourage the replier-consistency. Experimental results on two large conversation datasets show that our model outperforms the competitive baseline models significantly, and can generate diverse and replier-specific responses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2019-semi">
<titleInfo>
<title>A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinxin</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longbiao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifang</namePart>
<namePart type="family">Wang</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>Neural sequence-to-sequence models for dialog systems suffer from the problem of favoring uninformative and non replier-specific responses due to lack of the global and relevant information guidance. The existing methods model the generation process by leveraging the neural variational network with simple Gaussian. However, the sampled information from latent space usually becomes useless due to the KL divergence vanishing issue, and the highly abstractive global variables easily dilute the personal features of replier, leading to a non replier-specific response. Therefore, a novel Semi-Supervised Stable Variational Network (SSVN) is proposed to address these issues. We use a unit hypersperical distribution, namely the von Mises-Fisher (vMF), as the latent space of a semi-supervised model, which can obtain the stable KL performance by setting a fixed variance and hence enhance the global information representation. Meanwhile, an unsupervised extractor is introduced to automatically distill the replier-tailored feature which is then injected into a supervised generator to encourage the replier-consistency. Experimental results on two large conversation datasets show that our model outperforms the competitive baseline models significantly, and can generate diverse and replier-specific responses.</abstract>
<identifier type="citekey">chang-etal-2019-semi</identifier>
<identifier type="doi">10.18653/v1/D19-1200</identifier>
<location>
<url>https://aclanthology.org/D19-1200</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1920</start>
<end>1930</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation
%A Chang, Jinxin
%A He, Ruifang
%A Wang, Longbiao
%A Zhao, Xiangyu
%A Yang, Ting
%A Wang, Ruifang
%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 chang-etal-2019-semi
%X Neural sequence-to-sequence models for dialog systems suffer from the problem of favoring uninformative and non replier-specific responses due to lack of the global and relevant information guidance. The existing methods model the generation process by leveraging the neural variational network with simple Gaussian. However, the sampled information from latent space usually becomes useless due to the KL divergence vanishing issue, and the highly abstractive global variables easily dilute the personal features of replier, leading to a non replier-specific response. Therefore, a novel Semi-Supervised Stable Variational Network (SSVN) is proposed to address these issues. We use a unit hypersperical distribution, namely the von Mises-Fisher (vMF), as the latent space of a semi-supervised model, which can obtain the stable KL performance by setting a fixed variance and hence enhance the global information representation. Meanwhile, an unsupervised extractor is introduced to automatically distill the replier-tailored feature which is then injected into a supervised generator to encourage the replier-consistency. Experimental results on two large conversation datasets show that our model outperforms the competitive baseline models significantly, and can generate diverse and replier-specific responses.
%R 10.18653/v1/D19-1200
%U https://aclanthology.org/D19-1200
%U https://doi.org/10.18653/v1/D19-1200
%P 1920-1930
Markdown (Informal)
[A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation](https://aclanthology.org/D19-1200) (Chang et al., EMNLP-IJCNLP 2019)
ACL