@inproceedings{cui-etal-2020-mutual,
title = "{M}u{T}ual: A Dataset for Multi-Turn Dialogue Reasoning",
author = "Cui, Leyang and
Wu, Yu and
Liu, Shujie and
Zhang, Yue and
Zhou, Ming",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.130",
doi = "10.18653/v1/2020.acl-main.130",
pages = "1406--1416",
abstract = "Non-task oriented dialogue systems have achieved great success in recent years due to largely accessible conversation data and the development of deep learning techniques. Given a context, current systems are able to yield a relevant and fluent response, but sometimes make logical mistakes because of weak reasoning capabilities. To facilitate the conversation reasoning research, we introduce MuTual, a novel dataset for Multi-Turn dialogue Reasoning, consisting of 8,860 manually annotated dialogues based on Chinese student English listening comprehension exams. Compared to previous benchmarks for non-task oriented dialogue systems, MuTual is much more challenging since it requires a model that be able to handle various reasoning problems. Empirical results show that state-of-the-art methods only reach 71{\%}, which is far behind human performance of 94{\%}, indicating that there is ample room for improving reasoning ability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cui-etal-2020-mutual">
<titleInfo>
<title>MuTual: A Dataset for Multi-Turn Dialogue Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leyang</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shujie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</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>Non-task oriented dialogue systems have achieved great success in recent years due to largely accessible conversation data and the development of deep learning techniques. Given a context, current systems are able to yield a relevant and fluent response, but sometimes make logical mistakes because of weak reasoning capabilities. To facilitate the conversation reasoning research, we introduce MuTual, a novel dataset for Multi-Turn dialogue Reasoning, consisting of 8,860 manually annotated dialogues based on Chinese student English listening comprehension exams. Compared to previous benchmarks for non-task oriented dialogue systems, MuTual is much more challenging since it requires a model that be able to handle various reasoning problems. Empirical results show that state-of-the-art methods only reach 71%, which is far behind human performance of 94%, indicating that there is ample room for improving reasoning ability.</abstract>
<identifier type="citekey">cui-etal-2020-mutual</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.130</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.130</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>1406</start>
<end>1416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuTual: A Dataset for Multi-Turn Dialogue Reasoning
%A Cui, Leyang
%A Wu, Yu
%A Liu, Shujie
%A Zhang, Yue
%A Zhou, Ming
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F cui-etal-2020-mutual
%X Non-task oriented dialogue systems have achieved great success in recent years due to largely accessible conversation data and the development of deep learning techniques. Given a context, current systems are able to yield a relevant and fluent response, but sometimes make logical mistakes because of weak reasoning capabilities. To facilitate the conversation reasoning research, we introduce MuTual, a novel dataset for Multi-Turn dialogue Reasoning, consisting of 8,860 manually annotated dialogues based on Chinese student English listening comprehension exams. Compared to previous benchmarks for non-task oriented dialogue systems, MuTual is much more challenging since it requires a model that be able to handle various reasoning problems. Empirical results show that state-of-the-art methods only reach 71%, which is far behind human performance of 94%, indicating that there is ample room for improving reasoning ability.
%R 10.18653/v1/2020.acl-main.130
%U https://aclanthology.org/2020.acl-main.130
%U https://doi.org/10.18653/v1/2020.acl-main.130
%P 1406-1416
Markdown (Informal)
[MuTual: A Dataset for Multi-Turn Dialogue Reasoning](https://aclanthology.org/2020.acl-main.130) (Cui et al., ACL 2020)
ACL
- Leyang Cui, Yu Wu, Shujie Liu, Yue Zhang, and Ming Zhou. 2020. MuTual: A Dataset for Multi-Turn Dialogue Reasoning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1406–1416, Online. Association for Computational Linguistics.