@inproceedings{van-niekerk-etal-2020-knowing,
title = "Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles",
author = "van Niekerk, Carel and
Heck, Michael and
Geishauser, Christian and
Lin, Hsien-chin and
Lubis, Nurul and
Moresi, Marco and
Gasic, Milica",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.277",
doi = "10.18653/v1/2020.findings-emnlp.277",
pages = "3096--3102",
abstract = "The ability to accurately track what happens during a conversation is essential for the performance of a dialogue system. Current state-of-the-art multi-domain dialogue state trackers achieve just over 55{\%} accuracy on the current go-to benchmark, which means that in almost every second dialogue turn they place full confidence in an incorrect dialogue state. Belief trackers, on the other hand, maintain a distribution over possible dialogue states. However, they lack in performance compared to dialogue state trackers, and do not produce well calibrated distributions. In this work we present state-of-the-art performance in calibration for multi-domain dialogue belief trackers using a calibrated ensemble of models. Our resulting dialogue belief tracker also outperforms previous dialogue belief tracking models in terms of accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-niekerk-etal-2020-knowing">
<titleInfo>
<title>Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carel</namePart>
<namePart type="family">van Niekerk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Heck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Geishauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsien-chin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nurul</namePart>
<namePart type="family">Lubis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Moresi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gasic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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 ability to accurately track what happens during a conversation is essential for the performance of a dialogue system. Current state-of-the-art multi-domain dialogue state trackers achieve just over 55% accuracy on the current go-to benchmark, which means that in almost every second dialogue turn they place full confidence in an incorrect dialogue state. Belief trackers, on the other hand, maintain a distribution over possible dialogue states. However, they lack in performance compared to dialogue state trackers, and do not produce well calibrated distributions. In this work we present state-of-the-art performance in calibration for multi-domain dialogue belief trackers using a calibrated ensemble of models. Our resulting dialogue belief tracker also outperforms previous dialogue belief tracking models in terms of accuracy.</abstract>
<identifier type="citekey">van-niekerk-etal-2020-knowing</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.277</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.277</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3096</start>
<end>3102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles
%A van Niekerk, Carel
%A Heck, Michael
%A Geishauser, Christian
%A Lin, Hsien-chin
%A Lubis, Nurul
%A Moresi, Marco
%A Gasic, Milica
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F van-niekerk-etal-2020-knowing
%X The ability to accurately track what happens during a conversation is essential for the performance of a dialogue system. Current state-of-the-art multi-domain dialogue state trackers achieve just over 55% accuracy on the current go-to benchmark, which means that in almost every second dialogue turn they place full confidence in an incorrect dialogue state. Belief trackers, on the other hand, maintain a distribution over possible dialogue states. However, they lack in performance compared to dialogue state trackers, and do not produce well calibrated distributions. In this work we present state-of-the-art performance in calibration for multi-domain dialogue belief trackers using a calibrated ensemble of models. Our resulting dialogue belief tracker also outperforms previous dialogue belief tracking models in terms of accuracy.
%R 10.18653/v1/2020.findings-emnlp.277
%U https://aclanthology.org/2020.findings-emnlp.277
%U https://doi.org/10.18653/v1/2020.findings-emnlp.277
%P 3096-3102
Markdown (Informal)
[Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles](https://aclanthology.org/2020.findings-emnlp.277) (van Niekerk et al., Findings 2020)
ACL