@inproceedings{zou-etal-2018-memd,
title = "{MEMD}: A Diversity-Promoting Learning Framework for Short-Text Conversation",
author = "Zou, Meng and
Li, Xihan and
Liu, Haokun and
Deng, Zhihong",
editor = "Bender, Emily M. and
Derczynski, Leon and
Isabelle, Pierre",
booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/C18-1109",
pages = "1281--1291",
abstract = "Neural encoder-decoder models have been widely applied to conversational response generation, which is a research hot spot in recent years. However, conventional neural encoder-decoder models tend to generate commonplace responses like {``}I don{'}t know{''} regardless of what the input is. In this paper, we analyze this problem from a new perspective: latent vectors. Based on it, we propose an easy-to-extend learning framework named MEMD (Multi-Encoder to Multi-Decoder), in which an auxiliary encoder and an auxiliary decoder are introduced to provide necessary training guidance without resorting to extra data or complicating network{'}s inner structure. Experimental results demonstrate that our method effectively improve the quality of generated responses according to automatic metrics and human evaluations, yielding more diverse and smooth replies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zou-etal-2018-memd">
<titleInfo>
<title>MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xihan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haokun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Bender</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Isabelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural encoder-decoder models have been widely applied to conversational response generation, which is a research hot spot in recent years. However, conventional neural encoder-decoder models tend to generate commonplace responses like “I don’t know” regardless of what the input is. In this paper, we analyze this problem from a new perspective: latent vectors. Based on it, we propose an easy-to-extend learning framework named MEMD (Multi-Encoder to Multi-Decoder), in which an auxiliary encoder and an auxiliary decoder are introduced to provide necessary training guidance without resorting to extra data or complicating network’s inner structure. Experimental results demonstrate that our method effectively improve the quality of generated responses according to automatic metrics and human evaluations, yielding more diverse and smooth replies.</abstract>
<identifier type="citekey">zou-etal-2018-memd</identifier>
<location>
<url>https://aclanthology.org/C18-1109</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>1281</start>
<end>1291</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation
%A Zou, Meng
%A Li, Xihan
%A Liu, Haokun
%A Deng, Zhihong
%Y Bender, Emily M.
%Y Derczynski, Leon
%Y Isabelle, Pierre
%S Proceedings of the 27th International Conference on Computational Linguistics
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F zou-etal-2018-memd
%X Neural encoder-decoder models have been widely applied to conversational response generation, which is a research hot spot in recent years. However, conventional neural encoder-decoder models tend to generate commonplace responses like “I don’t know” regardless of what the input is. In this paper, we analyze this problem from a new perspective: latent vectors. Based on it, we propose an easy-to-extend learning framework named MEMD (Multi-Encoder to Multi-Decoder), in which an auxiliary encoder and an auxiliary decoder are introduced to provide necessary training guidance without resorting to extra data or complicating network’s inner structure. Experimental results demonstrate that our method effectively improve the quality of generated responses according to automatic metrics and human evaluations, yielding more diverse and smooth replies.
%U https://aclanthology.org/C18-1109
%P 1281-1291
Markdown (Informal)
[MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation](https://aclanthology.org/C18-1109) (Zou et al., COLING 2018)
ACL