@inproceedings{dey-etal-2022-towards,
title = "Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances",
author = "Dey, Suvodip and
Kummara, Ramamohan and
Desarkar, Maunendra",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.35/",
doi = "10.18653/v1/2022.acl-short.35",
pages = "318--324",
abstract = "Dialogue State Tracking (DST) is primarily evaluated using Joint Goal Accuracy (JGA) defined as the fraction of turns where the ground-truth dialogue state exactly matches the prediction. Generally in DST, the dialogue state or belief state for a given turn contain all the intents shown by the user till that turn. Due to this cumulative nature of the belief state, it is difficult to get a correct prediction once a misprediction has occurred. Thus, although being a useful metric, it can be harsh at times and underestimate the true potential of a DST model. Moreover, an improvement in JGA can sometimes decrease the performance of turn-level or non-cumulative belief state prediction due to inconsistency in annotations. So, using JGA as the only metric for model selection may not be ideal for all scenarios. In this work, we discuss various evaluation metrics used for DST along with their shortcomings. To address the existing issues, we propose a new evaluation metric named Flexible Goal Accuracy (FGA). FGA is a generalized version of JGA. But unlike JGA, it tries to give penalized rewards to mispredictions that are locally correct i.e. the root cause of the error is an earlier turn. By doing so, FGA considers the performance of both cumulative and turn-level prediction flexibly and provides a better insight than the existing metrics. We also show that FGA is a better discriminator of DST model performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dey-etal-2022-towards">
<titleInfo>
<title>Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suvodip</namePart>
<namePart type="family">Dey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramamohan</namePart>
<namePart type="family">Kummara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maunendra</namePart>
<namePart type="family">Desarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue State Tracking (DST) is primarily evaluated using Joint Goal Accuracy (JGA) defined as the fraction of turns where the ground-truth dialogue state exactly matches the prediction. Generally in DST, the dialogue state or belief state for a given turn contain all the intents shown by the user till that turn. Due to this cumulative nature of the belief state, it is difficult to get a correct prediction once a misprediction has occurred. Thus, although being a useful metric, it can be harsh at times and underestimate the true potential of a DST model. Moreover, an improvement in JGA can sometimes decrease the performance of turn-level or non-cumulative belief state prediction due to inconsistency in annotations. So, using JGA as the only metric for model selection may not be ideal for all scenarios. In this work, we discuss various evaluation metrics used for DST along with their shortcomings. To address the existing issues, we propose a new evaluation metric named Flexible Goal Accuracy (FGA). FGA is a generalized version of JGA. But unlike JGA, it tries to give penalized rewards to mispredictions that are locally correct i.e. the root cause of the error is an earlier turn. By doing so, FGA considers the performance of both cumulative and turn-level prediction flexibly and provides a better insight than the existing metrics. We also show that FGA is a better discriminator of DST model performance.</abstract>
<identifier type="citekey">dey-etal-2022-towards</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.35</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.35/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>318</start>
<end>324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances
%A Dey, Suvodip
%A Kummara, Ramamohan
%A Desarkar, Maunendra
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F dey-etal-2022-towards
%X Dialogue State Tracking (DST) is primarily evaluated using Joint Goal Accuracy (JGA) defined as the fraction of turns where the ground-truth dialogue state exactly matches the prediction. Generally in DST, the dialogue state or belief state for a given turn contain all the intents shown by the user till that turn. Due to this cumulative nature of the belief state, it is difficult to get a correct prediction once a misprediction has occurred. Thus, although being a useful metric, it can be harsh at times and underestimate the true potential of a DST model. Moreover, an improvement in JGA can sometimes decrease the performance of turn-level or non-cumulative belief state prediction due to inconsistency in annotations. So, using JGA as the only metric for model selection may not be ideal for all scenarios. In this work, we discuss various evaluation metrics used for DST along with their shortcomings. To address the existing issues, we propose a new evaluation metric named Flexible Goal Accuracy (FGA). FGA is a generalized version of JGA. But unlike JGA, it tries to give penalized rewards to mispredictions that are locally correct i.e. the root cause of the error is an earlier turn. By doing so, FGA considers the performance of both cumulative and turn-level prediction flexibly and provides a better insight than the existing metrics. We also show that FGA is a better discriminator of DST model performance.
%R 10.18653/v1/2022.acl-short.35
%U https://aclanthology.org/2022.acl-short.35/
%U https://doi.org/10.18653/v1/2022.acl-short.35
%P 318-324
Markdown (Informal)
[Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances](https://aclanthology.org/2022.acl-short.35/) (Dey et al., ACL 2022)
ACL