@inproceedings{qian-etal-2021-annotation,
title = "Annotation Inconsistency and Entity Bias in {M}ulti{WOZ}",
author = "Qian, Kun and
Beirami, Ahmad and
Lin, Zhouhan and
De, Ankita and
Geramifard, Alborz and
Yu, Zhou and
Sankar, Chinnadhurai",
editor = "Li, Haizhou and
Levow, Gina-Anne and
Yu, Zhou and
Gupta, Chitralekha and
Sisman, Berrak and
Cai, Siqi and
Vandyke, David and
Dethlefs, Nina and
Wu, Yan and
Li, Junyi Jessy",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.35/",
doi = "10.18653/v1/2021.sigdial-1.35",
pages = "326--337",
abstract = "MultiWOZ (Budzianowski et al., 2018) is one of the most popular multi-domain taskoriented dialog datasets, containing 10K+ annotated dialogs covering eight domains. It has been widely accepted as a benchmark for various dialog tasks, e.g., dialog state tracking (DST), natural language generation (NLG) and end-to-end (E2E) dialog modeling. In this work, we identify an overlooked issue with dialog state annotation inconsistencies in the dataset, where a slot type is tagged inconsistently across similar dialogs leading to confusion for DST modeling. We propose an automated correction for this issue, which is present in 70{\%} of the dialogs. Additionally, we notice that there is significant entity bias in the dataset (e.g., {\textquotedblleft}cambridge{\textquotedblright} appears in 50{\%} of the destination cities in the train domain). The entity bias can potentially lead to named entity memorization in generative models, which may go unnoticed as the test set suffers from a similar entity bias as well. We release a new test set with all entities replaced with unseen entities. Finally, we benchmark joint goal accuracy (JGA) of the state-of-theart DST baselines on these modified versions of the data. Our experiments show that the annotation inconsistency corrections lead to 7-10{\%} improvement in JGA. On the other hand, we observe a 29{\%} drop in JGA when models are evaluated on the new test set with unseen entities."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-etal-2021-annotation">
<titleInfo>
<title>Annotation Inconsistency and Entity Bias in MultiWOZ</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Beirami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhouhan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankita</namePart>
<namePart type="family">De</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alborz</namePart>
<namePart type="family">Geramifard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chinnadhurai</namePart>
<namePart type="family">Sankar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitralekha</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>MultiWOZ (Budzianowski et al., 2018) is one of the most popular multi-domain taskoriented dialog datasets, containing 10K+ annotated dialogs covering eight domains. It has been widely accepted as a benchmark for various dialog tasks, e.g., dialog state tracking (DST), natural language generation (NLG) and end-to-end (E2E) dialog modeling. In this work, we identify an overlooked issue with dialog state annotation inconsistencies in the dataset, where a slot type is tagged inconsistently across similar dialogs leading to confusion for DST modeling. We propose an automated correction for this issue, which is present in 70% of the dialogs. Additionally, we notice that there is significant entity bias in the dataset (e.g., “cambridge” appears in 50% of the destination cities in the train domain). The entity bias can potentially lead to named entity memorization in generative models, which may go unnoticed as the test set suffers from a similar entity bias as well. We release a new test set with all entities replaced with unseen entities. Finally, we benchmark joint goal accuracy (JGA) of the state-of-theart DST baselines on these modified versions of the data. Our experiments show that the annotation inconsistency corrections lead to 7-10% improvement in JGA. On the other hand, we observe a 29% drop in JGA when models are evaluated on the new test set with unseen entities.</abstract>
<identifier type="citekey">qian-etal-2021-annotation</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.35</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.35/</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>326</start>
<end>337</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotation Inconsistency and Entity Bias in MultiWOZ
%A Qian, Kun
%A Beirami, Ahmad
%A Lin, Zhouhan
%A De, Ankita
%A Geramifard, Alborz
%A Yu, Zhou
%A Sankar, Chinnadhurai
%Y Li, Haizhou
%Y Levow, Gina-Anne
%Y Yu, Zhou
%Y Gupta, Chitralekha
%Y Sisman, Berrak
%Y Cai, Siqi
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Wu, Yan
%Y Li, Junyi Jessy
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 July
%I Association for Computational Linguistics
%C Singapore and Online
%F qian-etal-2021-annotation
%X MultiWOZ (Budzianowski et al., 2018) is one of the most popular multi-domain taskoriented dialog datasets, containing 10K+ annotated dialogs covering eight domains. It has been widely accepted as a benchmark for various dialog tasks, e.g., dialog state tracking (DST), natural language generation (NLG) and end-to-end (E2E) dialog modeling. In this work, we identify an overlooked issue with dialog state annotation inconsistencies in the dataset, where a slot type is tagged inconsistently across similar dialogs leading to confusion for DST modeling. We propose an automated correction for this issue, which is present in 70% of the dialogs. Additionally, we notice that there is significant entity bias in the dataset (e.g., “cambridge” appears in 50% of the destination cities in the train domain). The entity bias can potentially lead to named entity memorization in generative models, which may go unnoticed as the test set suffers from a similar entity bias as well. We release a new test set with all entities replaced with unseen entities. Finally, we benchmark joint goal accuracy (JGA) of the state-of-theart DST baselines on these modified versions of the data. Our experiments show that the annotation inconsistency corrections lead to 7-10% improvement in JGA. On the other hand, we observe a 29% drop in JGA when models are evaluated on the new test set with unseen entities.
%R 10.18653/v1/2021.sigdial-1.35
%U https://aclanthology.org/2021.sigdial-1.35/
%U https://doi.org/10.18653/v1/2021.sigdial-1.35
%P 326-337
Markdown (Informal)
[Annotation Inconsistency and Entity Bias in MultiWOZ](https://aclanthology.org/2021.sigdial-1.35/) (Qian et al., SIGDIAL 2021)
ACL
- Kun Qian, Ahmad Beirami, Zhouhan Lin, Ankita De, Alborz Geramifard, Zhou Yu, and Chinnadhurai Sankar. 2021. Annotation Inconsistency and Entity Bias in MultiWOZ. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 326–337, Singapore and Online. Association for Computational Linguistics.