@inproceedings{kunilovskaya-etal-2024-mitigating,
title = "Mitigating Translationese with {GPT}-4: Strategies and Performance",
author = "Kunilovskaya, Maria and
Dutta Chowdhury, Koel and
Przybyl, Heike and
Espa{\~n}a-Bonet, Cristina and
Genabith, Josef",
editor = "Scarton, Carolina and
Prescott, Charlotte and
Bayliss, Chris and
Oakley, Chris and
Wright, Joanna and
Wrigley, Stuart and
Song, Xingyi and
Gow-Smith, Edward and
Bawden, Rachel and
S{\'a}nchez-Cartagena, V{\'\i}ctor M and
Cadwell, Patrick and
Lapshinova-Koltunski, Ekaterina and
Cabarr{\~a}o, Vera and
Chatzitheodorou, Konstantinos and
Nurminen, Mary and
Kanojia, Diptesh and
Moniz, Helena",
booktitle = "Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)",
month = jun,
year = "2024",
address = "Sheffield, UK",
publisher = "European Association for Machine Translation (EAMT)",
url = "https://aclanthology.org/2024.eamt-1.35",
pages = "411--430",
abstract = "Translations differ in systematic ways from texts originally authored in the same language.These differences, collectively known as translationese, can pose challenges in cross-lingual natural language processing: models trained or tested on translated input might struggle when presented with non-translated language. Translationese mitigation can alleviate this problem. This study investigates the generative capacities of GPT-4 to reduce translationese in human-translated texts. The task is framed as a rewriting process aimed at modified translations indistinguishable from the original text in the target language. Our focus is on prompt engineering that tests the utility of linguistic knowledge as part of the instruction for GPT-4. Through a series of prompt design experiments, we show that GPT4-generated revisions are more similar to originals in the target language when the prompts incorporate specific linguistic instructions instead of relying solely on the model{'}s internal knowledge. Furthermore, we release the segment-aligned bidirectional German-English data built from the Europarl corpus that underpins this study.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kunilovskaya-etal-2024-mitigating">
<titleInfo>
<title>Mitigating Translationese with GPT-4: Strategies and Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koel</namePart>
<namePart type="family">Dutta Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Przybyl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">España-Bonet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlotte</namePart>
<namePart type="family">Prescott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Bayliss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Oakley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Wright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stuart</namePart>
<namePart type="family">Wrigley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingyi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Gow-Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Cadwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Cabarrão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="family">Chatzitheodorou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diptesh</namePart>
<namePart type="family">Kanojia</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>
<originInfo>
<publisher>European Association for Machine Translation (EAMT)</publisher>
<place>
<placeTerm type="text">Sheffield, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translations differ in systematic ways from texts originally authored in the same language.These differences, collectively known as translationese, can pose challenges in cross-lingual natural language processing: models trained or tested on translated input might struggle when presented with non-translated language. Translationese mitigation can alleviate this problem. This study investigates the generative capacities of GPT-4 to reduce translationese in human-translated texts. The task is framed as a rewriting process aimed at modified translations indistinguishable from the original text in the target language. Our focus is on prompt engineering that tests the utility of linguistic knowledge as part of the instruction for GPT-4. Through a series of prompt design experiments, we show that GPT4-generated revisions are more similar to originals in the target language when the prompts incorporate specific linguistic instructions instead of relying solely on the model’s internal knowledge. Furthermore, we release the segment-aligned bidirectional German-English data built from the Europarl corpus that underpins this study.</abstract>
<identifier type="citekey">kunilovskaya-etal-2024-mitigating</identifier>
<location>
<url>https://aclanthology.org/2024.eamt-1.35</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>411</start>
<end>430</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Translationese with GPT-4: Strategies and Performance
%A Kunilovskaya, Maria
%A Dutta Chowdhury, Koel
%A Przybyl, Heike
%A España-Bonet, Cristina
%A Genabith, Josef
%Y Scarton, Carolina
%Y Prescott, Charlotte
%Y Bayliss, Chris
%Y Oakley, Chris
%Y Wright, Joanna
%Y Wrigley, Stuart
%Y Song, Xingyi
%Y Gow-Smith, Edward
%Y Bawden, Rachel
%Y Sánchez-Cartagena, Víctor M.
%Y Cadwell, Patrick
%Y Lapshinova-Koltunski, Ekaterina
%Y Cabarrão, Vera
%Y Chatzitheodorou, Konstantinos
%Y Nurminen, Mary
%Y Kanojia, Diptesh
%Y Moniz, Helena
%S Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2024
%8 June
%I European Association for Machine Translation (EAMT)
%C Sheffield, UK
%F kunilovskaya-etal-2024-mitigating
%X Translations differ in systematic ways from texts originally authored in the same language.These differences, collectively known as translationese, can pose challenges in cross-lingual natural language processing: models trained or tested on translated input might struggle when presented with non-translated language. Translationese mitigation can alleviate this problem. This study investigates the generative capacities of GPT-4 to reduce translationese in human-translated texts. The task is framed as a rewriting process aimed at modified translations indistinguishable from the original text in the target language. Our focus is on prompt engineering that tests the utility of linguistic knowledge as part of the instruction for GPT-4. Through a series of prompt design experiments, we show that GPT4-generated revisions are more similar to originals in the target language when the prompts incorporate specific linguistic instructions instead of relying solely on the model’s internal knowledge. Furthermore, we release the segment-aligned bidirectional German-English data built from the Europarl corpus that underpins this study.
%U https://aclanthology.org/2024.eamt-1.35
%P 411-430
Markdown (Informal)
[Mitigating Translationese with GPT-4: Strategies and Performance](https://aclanthology.org/2024.eamt-1.35) (Kunilovskaya et al., EAMT 2024)
ACL
- Maria Kunilovskaya, Koel Dutta Chowdhury, Heike Przybyl, Cristina España-Bonet, and Josef Genabith. 2024. Mitigating Translationese with GPT-4: Strategies and Performance. In Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1), pages 411–430, Sheffield, UK. European Association for Machine Translation (EAMT).