@inproceedings{xiang-etal-2022-investigating,
title = "Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics",
author = "Xiang, Jiannan and
Li, Huayang and
Liu, Yahui and
Liu, Lemao and
Huang, Guoping and
Lian, Defu and
Shi, Shuming",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.14",
doi = "10.18653/v1/2022.findings-acl.14",
pages = "150--157",
abstract = "Current practices in metric evaluation focus on one single dataset, e.g., Newstest dataset in each year{'}s WMT Metrics Shared Task. However, in this paper, we qualitatively and quantitatively show that the performances of metrics are sensitive to data. The ranking of metrics varies when the evaluation is conducted on different datasets. Then this paper further investigates two potential hypotheses, i.e., insignificant data points and the deviation of i.i.d assumption, which may take responsibility for the issue of data variance. In conclusion, our findings suggest that when evaluating automatic translation metrics, researchers should take data variance into account and be cautious to report the results on unreliable datasets, because it may leads to inconsistent results with most of the other datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiang-etal-2022-investigating">
<titleInfo>
<title>Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiannan</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huayang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yahui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lemao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoping</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Defu</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</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>Findings of the Association for Computational Linguistics: ACL 2022</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>Current practices in metric evaluation focus on one single dataset, e.g., Newstest dataset in each year’s WMT Metrics Shared Task. However, in this paper, we qualitatively and quantitatively show that the performances of metrics are sensitive to data. The ranking of metrics varies when the evaluation is conducted on different datasets. Then this paper further investigates two potential hypotheses, i.e., insignificant data points and the deviation of i.i.d assumption, which may take responsibility for the issue of data variance. In conclusion, our findings suggest that when evaluating automatic translation metrics, researchers should take data variance into account and be cautious to report the results on unreliable datasets, because it may leads to inconsistent results with most of the other datasets.</abstract>
<identifier type="citekey">xiang-etal-2022-investigating</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.14</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.14</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>150</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics
%A Xiang, Jiannan
%A Li, Huayang
%A Liu, Yahui
%A Liu, Lemao
%A Huang, Guoping
%A Lian, Defu
%A Shi, Shuming
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F xiang-etal-2022-investigating
%X Current practices in metric evaluation focus on one single dataset, e.g., Newstest dataset in each year’s WMT Metrics Shared Task. However, in this paper, we qualitatively and quantitatively show that the performances of metrics are sensitive to data. The ranking of metrics varies when the evaluation is conducted on different datasets. Then this paper further investigates two potential hypotheses, i.e., insignificant data points and the deviation of i.i.d assumption, which may take responsibility for the issue of data variance. In conclusion, our findings suggest that when evaluating automatic translation metrics, researchers should take data variance into account and be cautious to report the results on unreliable datasets, because it may leads to inconsistent results with most of the other datasets.
%R 10.18653/v1/2022.findings-acl.14
%U https://aclanthology.org/2022.findings-acl.14
%U https://doi.org/10.18653/v1/2022.findings-acl.14
%P 150-157
Markdown (Informal)
[Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics](https://aclanthology.org/2022.findings-acl.14) (Xiang et al., Findings 2022)
ACL