@inproceedings{nekvinda-dusek-2021-shades,
title = "Shades of {BLEU}, Flavours of Success: The Case of {M}ulti{WOZ}",
author = "Nekvinda, Tom{\'a}{\v{s}} and
Du{\v{s}}ek, Ond{\v{r}}ej",
editor = "Bosselut, Antoine and
Durmus, Esin and
Gangal, Varun Prashant and
Gehrmann, Sebastian and
Jernite, Yacine and
Perez-Beltrachini, Laura and
Shaikh, Samira and
Xu, Wei",
booktitle = "Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.gem-1.4",
doi = "10.18653/v1/2021.gem-1.4",
pages = "34--46",
abstract = "The MultiWOZ dataset (Budzianowski et al.,2018) is frequently used for benchmarkingcontext-to-response abilities of task-orienteddialogue systems. In this work, we identifyinconsistencies in data preprocessing and re-porting of three corpus-based metrics used onthis dataset, i.e., BLEU score and Inform {\&}Success rates. We point out a few problemsof the MultiWOZ benchmark such as unsat-isfactory preprocessing, insufficient or under-specified evaluation metrics, or rigid database. We re-evaluate 7 end-to-end and 6 policy opti-mization models in as-fair-as-possible setups,and we show that their reported scores cannotbe directly compared. To facilitate compari-son of future systems, we release our stand-alone standardized evaluation scripts. We alsogive basic recommendations for corpus-basedbenchmarking in future works.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nekvinda-dusek-2021-shades">
<titleInfo>
<title>Shades of BLEU, Flavours of Success: The Case of MultiWOZ</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Nekvinda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esin</namePart>
<namePart type="family">Durmus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="given">Prashant</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</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>The MultiWOZ dataset (Budzianowski et al.,2018) is frequently used for benchmarkingcontext-to-response abilities of task-orienteddialogue systems. In this work, we identifyinconsistencies in data preprocessing and re-porting of three corpus-based metrics used onthis dataset, i.e., BLEU score and Inform &Success rates. We point out a few problemsof the MultiWOZ benchmark such as unsat-isfactory preprocessing, insufficient or under-specified evaluation metrics, or rigid database. We re-evaluate 7 end-to-end and 6 policy opti-mization models in as-fair-as-possible setups,and we show that their reported scores cannotbe directly compared. To facilitate compari-son of future systems, we release our stand-alone standardized evaluation scripts. We alsogive basic recommendations for corpus-basedbenchmarking in future works.</abstract>
<identifier type="citekey">nekvinda-dusek-2021-shades</identifier>
<identifier type="doi">10.18653/v1/2021.gem-1.4</identifier>
<location>
<url>https://aclanthology.org/2021.gem-1.4</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>34</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Shades of BLEU, Flavours of Success: The Case of MultiWOZ
%A Nekvinda, Tomáš
%A Dušek, Ondřej
%Y Bosselut, Antoine
%Y Durmus, Esin
%Y Gangal, Varun Prashant
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Perez-Beltrachini, Laura
%Y Shaikh, Samira
%Y Xu, Wei
%S Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F nekvinda-dusek-2021-shades
%X The MultiWOZ dataset (Budzianowski et al.,2018) is frequently used for benchmarkingcontext-to-response abilities of task-orienteddialogue systems. In this work, we identifyinconsistencies in data preprocessing and re-porting of three corpus-based metrics used onthis dataset, i.e., BLEU score and Inform &Success rates. We point out a few problemsof the MultiWOZ benchmark such as unsat-isfactory preprocessing, insufficient or under-specified evaluation metrics, or rigid database. We re-evaluate 7 end-to-end and 6 policy opti-mization models in as-fair-as-possible setups,and we show that their reported scores cannotbe directly compared. To facilitate compari-son of future systems, we release our stand-alone standardized evaluation scripts. We alsogive basic recommendations for corpus-basedbenchmarking in future works.
%R 10.18653/v1/2021.gem-1.4
%U https://aclanthology.org/2021.gem-1.4
%U https://doi.org/10.18653/v1/2021.gem-1.4
%P 34-46
Markdown (Informal)
[Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://aclanthology.org/2021.gem-1.4) (Nekvinda & Dušek, GEM 2021)
ACL