@inproceedings{liao-etal-2025-culture,
title = "Culture-aware machine translation: the case study of low-resource language pair {C}atalan-{C}hinese",
author = "Liao, Xixian and
Escolano, Carlos and
Mash, Audrey and
Fornaciari, Francesca De Luca and
Gilabert, Javier Garc{\'i}a and
Argote, Miguel Claramunt and
Bohman, Ella and
Melero, Maite",
editor = "Bouillon, Pierrette and
Gerlach, Johanna and
Girletti, Sabrina and
Volkart, Lise and
Rubino, Raphael and
Sennrich, Rico and
Farinha, Ana C. and
Gaido, Marco and
Daems, Joke and
Kenny, Dorothy and
Moniz, Helena and
Szoc, Sara",
booktitle = "Proceedings of Machine Translation Summit XX: Volume 1",
month = jun,
year = "2025",
address = "Geneva, Switzerland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2025.mtsummit-1.12/",
pages = "150--161",
ISBN = "978-2-9701897-0-1",
abstract = "High-quality machine translation requires datasets that not only ensure linguistic accuracy but also capture regional and cultural nuances. While many existing benchmarks, such as FLORES-200, rely on English as a pivot language, this approach can overlook the specificity of direct language pairs, particularly for underrepresented combinations like Catalan-Chinese. In this study, we demonstrate that even with a relatively small dataset of approximately 1,000 sentences, we can significantly improve MT localization. To this end, we introduce a dataset specifically designed to enhance Catalan-to-Chinese translation by prioritizing regionally and culturally specific topics. Unlike pivot-based datasets, our data source ensures a more faithful representation of Catalan linguistic and cultural elements, leading to more accurate translations of local terms and expressions. Using this dataset, we demonstrate better performance over the English-pivot FLORES-200 dev set and achieve competitive results on the FLORES-200 devtest set when evaluated with neural-based metrics. We release this dataset as both a human-preference resource and a benchmark for Catalan-Chinese translation. Additionally, we include Spanish translations for each sentence, facilitating extensions to Spanish-Chinese translation tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liao-etal-2025-culture">
<titleInfo>
<title>Culture-aware machine translation: the case study of low-resource language pair Catalan-Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xixian</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Escolano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Audrey</namePart>
<namePart type="family">Mash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="given">De</namePart>
<namePart type="given">Luca</namePart>
<namePart type="family">Fornaciari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="given">García</namePart>
<namePart type="family">Gilabert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Claramunt</namePart>
<namePart type="family">Argote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ella</namePart>
<namePart type="family">Bohman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XX: Volume 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierrette</namePart>
<namePart type="family">Bouillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Gerlach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Girletti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lise</namePart>
<namePart type="family">Volkart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Rubino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Farinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Daems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorothy</namePart>
<namePart type="family">Kenny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Szoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Geneva, Switzerland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-2-9701897-0-1</identifier>
</relatedItem>
<abstract>High-quality machine translation requires datasets that not only ensure linguistic accuracy but also capture regional and cultural nuances. While many existing benchmarks, such as FLORES-200, rely on English as a pivot language, this approach can overlook the specificity of direct language pairs, particularly for underrepresented combinations like Catalan-Chinese. In this study, we demonstrate that even with a relatively small dataset of approximately 1,000 sentences, we can significantly improve MT localization. To this end, we introduce a dataset specifically designed to enhance Catalan-to-Chinese translation by prioritizing regionally and culturally specific topics. Unlike pivot-based datasets, our data source ensures a more faithful representation of Catalan linguistic and cultural elements, leading to more accurate translations of local terms and expressions. Using this dataset, we demonstrate better performance over the English-pivot FLORES-200 dev set and achieve competitive results on the FLORES-200 devtest set when evaluated with neural-based metrics. We release this dataset as both a human-preference resource and a benchmark for Catalan-Chinese translation. Additionally, we include Spanish translations for each sentence, facilitating extensions to Spanish-Chinese translation tasks.</abstract>
<identifier type="citekey">liao-etal-2025-culture</identifier>
<location>
<url>https://aclanthology.org/2025.mtsummit-1.12/</url>
</location>
<part>
<date>2025-06</date>
<extent unit="page">
<start>150</start>
<end>161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Culture-aware machine translation: the case study of low-resource language pair Catalan-Chinese
%A Liao, Xixian
%A Escolano, Carlos
%A Mash, Audrey
%A Fornaciari, Francesca De Luca
%A Gilabert, Javier García
%A Argote, Miguel Claramunt
%A Bohman, Ella
%A Melero, Maite
%Y Bouillon, Pierrette
%Y Gerlach, Johanna
%Y Girletti, Sabrina
%Y Volkart, Lise
%Y Rubino, Raphael
%Y Sennrich, Rico
%Y Farinha, Ana C.
%Y Gaido, Marco
%Y Daems, Joke
%Y Kenny, Dorothy
%Y Moniz, Helena
%Y Szoc, Sara
%S Proceedings of Machine Translation Summit XX: Volume 1
%D 2025
%8 June
%I European Association for Machine Translation
%C Geneva, Switzerland
%@ 978-2-9701897-0-1
%F liao-etal-2025-culture
%X High-quality machine translation requires datasets that not only ensure linguistic accuracy but also capture regional and cultural nuances. While many existing benchmarks, such as FLORES-200, rely on English as a pivot language, this approach can overlook the specificity of direct language pairs, particularly for underrepresented combinations like Catalan-Chinese. In this study, we demonstrate that even with a relatively small dataset of approximately 1,000 sentences, we can significantly improve MT localization. To this end, we introduce a dataset specifically designed to enhance Catalan-to-Chinese translation by prioritizing regionally and culturally specific topics. Unlike pivot-based datasets, our data source ensures a more faithful representation of Catalan linguistic and cultural elements, leading to more accurate translations of local terms and expressions. Using this dataset, we demonstrate better performance over the English-pivot FLORES-200 dev set and achieve competitive results on the FLORES-200 devtest set when evaluated with neural-based metrics. We release this dataset as both a human-preference resource and a benchmark for Catalan-Chinese translation. Additionally, we include Spanish translations for each sentence, facilitating extensions to Spanish-Chinese translation tasks.
%U https://aclanthology.org/2025.mtsummit-1.12/
%P 150-161
Markdown (Informal)
[Culture-aware machine translation: the case study of low-resource language pair Catalan-Chinese](https://aclanthology.org/2025.mtsummit-1.12/) (Liao et al., MTSummit 2025)
ACL
- Xixian Liao, Carlos Escolano, Audrey Mash, Francesca De Luca Fornaciari, Javier García Gilabert, Miguel Claramunt Argote, Ella Bohman, and Maite Melero. 2025. Culture-aware machine translation: the case study of low-resource language pair Catalan-Chinese. In Proceedings of Machine Translation Summit XX: Volume 1, pages 150–161, Geneva, Switzerland. European Association for Machine Translation.