@inproceedings{wang-kageura-2026-context,
title = "Context-8: A Data Set for Evaluating Context Sensitivity in Machine Translation",
author = "Wang, Dongyue and
Kageura, Kyo",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.385/",
doi = "10.63317/3cawdf257c7e",
pages = "4902--4920",
abstract = "Context plays a crucial role in translation, enhancing both accuracy and fluency. With the advancement of machine translation (MT), the concept of context is now considered across an increasingly broader range of phenomena. Despite its importance, however, systematic definitions of context provided by communication studies and translation studies remain fragmented, and the concept of context remains elusive in MT research. To the best of our knowledge, no dataset currently exists that comprehensively evaluates MT{'}s sensitivity to context. In this study, we propose a systematic taxonomy of context and introduce Context-8, an evaluation dataset designed to assess context sensitivity in MT for English-to-Japanese translation. The initial release includes 130 groups comprising 533 English-to-Japanese translation examples, each requiring different context categories to produce accurate and fluent translations. The data are taken from both hand-crafted and online materials. We release Context-8 to support the evaluation and benchmarking of MT systems with respect to context sensitivity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-kageura-2026-context">
<titleInfo>
<title>Context-8: A Data Set for Evaluating Context Sensitivity in Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyo</namePart>
<namePart type="family">Kageura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Context plays a crucial role in translation, enhancing both accuracy and fluency. With the advancement of machine translation (MT), the concept of context is now considered across an increasingly broader range of phenomena. Despite its importance, however, systematic definitions of context provided by communication studies and translation studies remain fragmented, and the concept of context remains elusive in MT research. To the best of our knowledge, no dataset currently exists that comprehensively evaluates MT’s sensitivity to context. In this study, we propose a systematic taxonomy of context and introduce Context-8, an evaluation dataset designed to assess context sensitivity in MT for English-to-Japanese translation. The initial release includes 130 groups comprising 533 English-to-Japanese translation examples, each requiring different context categories to produce accurate and fluent translations. The data are taken from both hand-crafted and online materials. We release Context-8 to support the evaluation and benchmarking of MT systems with respect to context sensitivity.</abstract>
<identifier type="citekey">wang-kageura-2026-context</identifier>
<identifier type="doi">10.63317/3cawdf257c7e</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.385/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4902</start>
<end>4920</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context-8: A Data Set for Evaluating Context Sensitivity in Machine Translation
%A Wang, Dongyue
%A Kageura, Kyo
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F wang-kageura-2026-context
%X Context plays a crucial role in translation, enhancing both accuracy and fluency. With the advancement of machine translation (MT), the concept of context is now considered across an increasingly broader range of phenomena. Despite its importance, however, systematic definitions of context provided by communication studies and translation studies remain fragmented, and the concept of context remains elusive in MT research. To the best of our knowledge, no dataset currently exists that comprehensively evaluates MT’s sensitivity to context. In this study, we propose a systematic taxonomy of context and introduce Context-8, an evaluation dataset designed to assess context sensitivity in MT for English-to-Japanese translation. The initial release includes 130 groups comprising 533 English-to-Japanese translation examples, each requiring different context categories to produce accurate and fluent translations. The data are taken from both hand-crafted and online materials. We release Context-8 to support the evaluation and benchmarking of MT systems with respect to context sensitivity.
%R 10.63317/3cawdf257c7e
%U https://aclanthology.org/2026.lrec-1.385/
%U https://doi.org/10.63317/3cawdf257c7e
%P 4902-4920
Markdown (Informal)
[Context-8: A Data Set for Evaluating Context Sensitivity in Machine Translation](https://aclanthology.org/2026.lrec-1.385/) (Wang & Kageura, LREC 2026)
ACL