@inproceedings{phy-etal-2020-deconstruct,
title = "Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems",
author = "Phy, Vitou and
Zhao, Yang and
Aizawa, Akiko",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.368",
doi = "10.18653/v1/2020.coling-main.368",
pages = "4164--4178",
abstract = "Many automatic evaluation metrics have been proposed to score the overall quality of a response in open-domain dialogue. Generally, the overall quality is comprised of various aspects, such as relevancy, specificity, and empathy, and the importance of each aspect differs according to the task. For instance, specificity is mandatory in a food-ordering dialogue task, whereas fluency is preferred in a language-teaching dialogue system. However, existing metrics are not designed to cope with such flexibility. For example, BLEU score fundamentally relies only on word overlapping, whereas BERTScore relies on semantic similarity between reference and candidate response. Thus, they are not guaranteed to capture the required aspects, i.e., specificity. To design a metric that is flexible to a task, we first propose making these qualities manageable by grouping them into three groups: understandability, sensibleness, and likability, where likability is a combination of qualities that are essential for a task. We also propose a simple method to composite metrics of each aspect to obtain a single metric called USL-H, which stands for Understandability, Sensibleness, and Likability in Hierarchy. We demonstrated that USL-H score achieves good correlations with human judgment and maintains its configurability towards different aspects and metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="phy-etal-2020-deconstruct">
<titleInfo>
<title>Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vitou</namePart>
<namePart type="family">Phy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many automatic evaluation metrics have been proposed to score the overall quality of a response in open-domain dialogue. Generally, the overall quality is comprised of various aspects, such as relevancy, specificity, and empathy, and the importance of each aspect differs according to the task. For instance, specificity is mandatory in a food-ordering dialogue task, whereas fluency is preferred in a language-teaching dialogue system. However, existing metrics are not designed to cope with such flexibility. For example, BLEU score fundamentally relies only on word overlapping, whereas BERTScore relies on semantic similarity between reference and candidate response. Thus, they are not guaranteed to capture the required aspects, i.e., specificity. To design a metric that is flexible to a task, we first propose making these qualities manageable by grouping them into three groups: understandability, sensibleness, and likability, where likability is a combination of qualities that are essential for a task. We also propose a simple method to composite metrics of each aspect to obtain a single metric called USL-H, which stands for Understandability, Sensibleness, and Likability in Hierarchy. We demonstrated that USL-H score achieves good correlations with human judgment and maintains its configurability towards different aspects and metrics.</abstract>
<identifier type="citekey">phy-etal-2020-deconstruct</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.368</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.368</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4164</start>
<end>4178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems
%A Phy, Vitou
%A Zhao, Yang
%A Aizawa, Akiko
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F phy-etal-2020-deconstruct
%X Many automatic evaluation metrics have been proposed to score the overall quality of a response in open-domain dialogue. Generally, the overall quality is comprised of various aspects, such as relevancy, specificity, and empathy, and the importance of each aspect differs according to the task. For instance, specificity is mandatory in a food-ordering dialogue task, whereas fluency is preferred in a language-teaching dialogue system. However, existing metrics are not designed to cope with such flexibility. For example, BLEU score fundamentally relies only on word overlapping, whereas BERTScore relies on semantic similarity between reference and candidate response. Thus, they are not guaranteed to capture the required aspects, i.e., specificity. To design a metric that is flexible to a task, we first propose making these qualities manageable by grouping them into three groups: understandability, sensibleness, and likability, where likability is a combination of qualities that are essential for a task. We also propose a simple method to composite metrics of each aspect to obtain a single metric called USL-H, which stands for Understandability, Sensibleness, and Likability in Hierarchy. We demonstrated that USL-H score achieves good correlations with human judgment and maintains its configurability towards different aspects and metrics.
%R 10.18653/v1/2020.coling-main.368
%U https://aclanthology.org/2020.coling-main.368
%U https://doi.org/10.18653/v1/2020.coling-main.368
%P 4164-4178
Markdown (Informal)
[Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems](https://aclanthology.org/2020.coling-main.368) (Phy et al., COLING 2020)
ACL