@inproceedings{eric-etal-2020-multiwoz,
title = "{M}ulti{WOZ} 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines",
author = "Eric, Mihail and
Goel, Rahul and
Paul, Shachi and
Sethi, Abhishek and
Agarwal, Sanchit and
Gao, Shuyang and
Kumar, Adarsh and
Goyal, Anuj and
Ku, Peter and
Hakkani-Tur, Dilek",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.53",
pages = "422--428",
abstract = "MultiWOZ 2.0 (Budzianowski et al., 2018) is a recently released multi-domain dialogue dataset spanning 7 distinct domains and containing over 10,000 dialogues. Though immensely useful and one of the largest resources of its kind to-date, MultiWOZ 2.0 has a few shortcomings. Firstly, there are substantial noise in the dialogue state annotations and dialogue utterances which negatively impact the performance of state-tracking models. Secondly, follow-up work (Lee et al., 2019) has augmented the original dataset with user dialogue acts. This leads to multiple co-existent versions of the same dataset with minor modifications. In this work we tackle the aforementioned issues by introducing MultiWOZ 2.1. To fix the noisy state annotations, we use crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset. This correction process results in changes to over 32{\%} of state annotations across 40{\%} of the dialogue turns. In addition, we fix 146 dialogue utterances by canonicalizing slot values in the utterances to the values in the dataset ontology. To address the second problem, we combined the contributions of the follow-up works into MultiWOZ 2.1. Hence, our dataset also includes user dialogue acts as well as multiple slot descriptions per dialogue state slot. We then benchmark a number of state-of-the-art dialogue state tracking models on the MultiWOZ 2.1 dataset and show the joint state tracking performance on the corrected state annotations. We are publicly releasing MultiWOZ 2.1 to the community, hoping that this dataset resource will allow for more effective models across various dialogue subproblems to be built in the future.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eric-etal-2020-multiwoz">
<titleInfo>
<title>MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mihail</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shachi</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Sethi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanchit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adarsh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>MultiWOZ 2.0 (Budzianowski et al., 2018) is a recently released multi-domain dialogue dataset spanning 7 distinct domains and containing over 10,000 dialogues. Though immensely useful and one of the largest resources of its kind to-date, MultiWOZ 2.0 has a few shortcomings. Firstly, there are substantial noise in the dialogue state annotations and dialogue utterances which negatively impact the performance of state-tracking models. Secondly, follow-up work (Lee et al., 2019) has augmented the original dataset with user dialogue acts. This leads to multiple co-existent versions of the same dataset with minor modifications. In this work we tackle the aforementioned issues by introducing MultiWOZ 2.1. To fix the noisy state annotations, we use crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset. This correction process results in changes to over 32% of state annotations across 40% of the dialogue turns. In addition, we fix 146 dialogue utterances by canonicalizing slot values in the utterances to the values in the dataset ontology. To address the second problem, we combined the contributions of the follow-up works into MultiWOZ 2.1. Hence, our dataset also includes user dialogue acts as well as multiple slot descriptions per dialogue state slot. We then benchmark a number of state-of-the-art dialogue state tracking models on the MultiWOZ 2.1 dataset and show the joint state tracking performance on the corrected state annotations. We are publicly releasing MultiWOZ 2.1 to the community, hoping that this dataset resource will allow for more effective models across various dialogue subproblems to be built in the future.</abstract>
<identifier type="citekey">eric-etal-2020-multiwoz</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.53</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>422</start>
<end>428</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines
%A Eric, Mihail
%A Goel, Rahul
%A Paul, Shachi
%A Sethi, Abhishek
%A Agarwal, Sanchit
%A Gao, Shuyang
%A Kumar, Adarsh
%A Goyal, Anuj
%A Ku, Peter
%A Hakkani-Tur, Dilek
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F eric-etal-2020-multiwoz
%X MultiWOZ 2.0 (Budzianowski et al., 2018) is a recently released multi-domain dialogue dataset spanning 7 distinct domains and containing over 10,000 dialogues. Though immensely useful and one of the largest resources of its kind to-date, MultiWOZ 2.0 has a few shortcomings. Firstly, there are substantial noise in the dialogue state annotations and dialogue utterances which negatively impact the performance of state-tracking models. Secondly, follow-up work (Lee et al., 2019) has augmented the original dataset with user dialogue acts. This leads to multiple co-existent versions of the same dataset with minor modifications. In this work we tackle the aforementioned issues by introducing MultiWOZ 2.1. To fix the noisy state annotations, we use crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset. This correction process results in changes to over 32% of state annotations across 40% of the dialogue turns. In addition, we fix 146 dialogue utterances by canonicalizing slot values in the utterances to the values in the dataset ontology. To address the second problem, we combined the contributions of the follow-up works into MultiWOZ 2.1. Hence, our dataset also includes user dialogue acts as well as multiple slot descriptions per dialogue state slot. We then benchmark a number of state-of-the-art dialogue state tracking models on the MultiWOZ 2.1 dataset and show the joint state tracking performance on the corrected state annotations. We are publicly releasing MultiWOZ 2.1 to the community, hoping that this dataset resource will allow for more effective models across various dialogue subproblems to be built in the future.
%U https://aclanthology.org/2020.lrec-1.53
%P 422-428
Markdown (Informal)
[MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines](https://aclanthology.org/2020.lrec-1.53) (Eric et al., LREC 2020)
ACL
- Mihail Eric, Rahul Goel, Shachi Paul, Abhishek Sethi, Sanchit Agarwal, Shuyang Gao, Adarsh Kumar, Anuj Goyal, Peter Ku, and Dilek Hakkani-Tur. 2020. MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 422–428, Marseille, France. European Language Resources Association.