@inproceedings{kocmi-etal-2024-error,
title = "Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation",
author = "Kocmi, Tom and
Zouhar, Vil{\'e}m and
Avramidis, Eleftherios and
Grundkiewicz, Roman and
Karpinska, Marzena and
Popovi{\'c}, Maja and
Sachan, Mrinmaya and
Shmatova, Mariya",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Ninth Conference on Machine Translation",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wmt-1.131",
doi = "10.18653/v1/2024.wmt-1.131",
pages = "1440--1453",
abstract = "High-quality Machine Translation (MT) evaluation relies heavily on human judgments.Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and can only be done by experts, whose availability may be limited especially for low-resource languages.On the other hand, just assigning overall scores, like Direct Assessment (DA), is simpler and faster and can be done by translators of any level, but is less reliable.In this paper, we introduce Error Span Annotation (ESA), a human evaluation protocol which combines the continuous rating of DA with the high-level error severity span marking of MQM.We validate ESA by comparing it to MQM and DA for 12 MT systems and one human reference translation (English to German) from WMT23. The results show that ESA offers faster and cheaper annotations than MQM at the same quality level, without the requirement of expensive MQM experts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kocmi-etal-2024-error">
<titleInfo>
<title>Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vilém</namePart>
<namePart type="family">Zouhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleftherios</namePart>
<namePart type="family">Avramidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Grundkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzena</namePart>
<namePart type="family">Karpinska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mrinmaya</namePart>
<namePart type="family">Sachan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariya</namePart>
<namePart type="family">Shmatova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>High-quality Machine Translation (MT) evaluation relies heavily on human judgments.Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and can only be done by experts, whose availability may be limited especially for low-resource languages.On the other hand, just assigning overall scores, like Direct Assessment (DA), is simpler and faster and can be done by translators of any level, but is less reliable.In this paper, we introduce Error Span Annotation (ESA), a human evaluation protocol which combines the continuous rating of DA with the high-level error severity span marking of MQM.We validate ESA by comparing it to MQM and DA for 12 MT systems and one human reference translation (English to German) from WMT23. The results show that ESA offers faster and cheaper annotations than MQM at the same quality level, without the requirement of expensive MQM experts.</abstract>
<identifier type="citekey">kocmi-etal-2024-error</identifier>
<identifier type="doi">10.18653/v1/2024.wmt-1.131</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.131</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1440</start>
<end>1453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation
%A Kocmi, Tom
%A Zouhar, Vilém
%A Avramidis, Eleftherios
%A Grundkiewicz, Roman
%A Karpinska, Marzena
%A Popović, Maja
%A Sachan, Mrinmaya
%A Shmatova, Mariya
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F kocmi-etal-2024-error
%X High-quality Machine Translation (MT) evaluation relies heavily on human judgments.Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and can only be done by experts, whose availability may be limited especially for low-resource languages.On the other hand, just assigning overall scores, like Direct Assessment (DA), is simpler and faster and can be done by translators of any level, but is less reliable.In this paper, we introduce Error Span Annotation (ESA), a human evaluation protocol which combines the continuous rating of DA with the high-level error severity span marking of MQM.We validate ESA by comparing it to MQM and DA for 12 MT systems and one human reference translation (English to German) from WMT23. The results show that ESA offers faster and cheaper annotations than MQM at the same quality level, without the requirement of expensive MQM experts.
%R 10.18653/v1/2024.wmt-1.131
%U https://aclanthology.org/2024.wmt-1.131
%U https://doi.org/10.18653/v1/2024.wmt-1.131
%P 1440-1453
Markdown (Informal)
[Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation](https://aclanthology.org/2024.wmt-1.131) (Kocmi et al., WMT 2024)
ACL
- Tom Kocmi, Vilém Zouhar, Eleftherios Avramidis, Roman Grundkiewicz, Marzena Karpinska, Maja Popović, Mrinmaya Sachan, and Mariya Shmatova. 2024. Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation. In Proceedings of the Ninth Conference on Machine Translation, pages 1440–1453, Miami, Florida, USA. Association for Computational Linguistics.