@inproceedings{uguet-etal-2024-llms,
title = "{LLM}s in Post-Translation Workflows: Comparing Performance in Post-Editing and Error Analysis",
author = "Uguet, Celia and
Bane, Fred and
Aymo, Mahmoud and
Torres, Jo{\~a}o and
Zaretskaya, Anna and
Blanch Mir{\'o}, T{\`a}nia Blanch Mir{\'o}",
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-1.32",
pages = "373--386",
abstract = "This study conducts a comprehensive comparison of three leading LLMs{---}GPT-4, Claude 3, and Gemini{---}in two translation-related tasks: automatic post-editing and MQM error annotation, across four languages. Utilizing the pharmaceutical EMEA corpus to maintain domain specificity and minimize data contamination, the research examines the models{'} performance in these two tasks. Our findings reveal the nuanced capabilities of LLMs in handling MTPE and MQM tasks, hinting at the potential of these models in streamlining and optimizing translation workflows. Future directions include fine-tuning LLMs for task-specific improvements and exploring the integration of style guides for enhanced translation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uguet-etal-2024-llms">
<titleInfo>
<title>LLMs in Post-Translation Workflows: Comparing Performance in Post-Editing and Error Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Celia</namePart>
<namePart type="family">Uguet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Bane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Aymo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Zaretskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tània</namePart>
<namePart type="given">Blanch</namePart>
<namePart type="given">Miró</namePart>
<namePart type="family">Blanch Miró</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>This study conducts a comprehensive comparison of three leading LLMs—GPT-4, Claude 3, and Gemini—in two translation-related tasks: automatic post-editing and MQM error annotation, across four languages. Utilizing the pharmaceutical EMEA corpus to maintain domain specificity and minimize data contamination, the research examines the models’ performance in these two tasks. Our findings reveal the nuanced capabilities of LLMs in handling MTPE and MQM tasks, hinting at the potential of these models in streamlining and optimizing translation workflows. Future directions include fine-tuning LLMs for task-specific improvements and exploring the integration of style guides for enhanced translation quality.</abstract>
<identifier type="citekey">uguet-etal-2024-llms</identifier>
<location>
<url>https://aclanthology.org/2024.eamt-1.32</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>373</start>
<end>386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMs in Post-Translation Workflows: Comparing Performance in Post-Editing and Error Analysis
%A Uguet, Celia
%A Bane, Fred
%A Aymo, Mahmoud
%A Torres, João
%A Zaretskaya, Anna
%A Blanch Miró, Tània Blanch Miró
%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 uguet-etal-2024-llms
%X This study conducts a comprehensive comparison of three leading LLMs—GPT-4, Claude 3, and Gemini—in two translation-related tasks: automatic post-editing and MQM error annotation, across four languages. Utilizing the pharmaceutical EMEA corpus to maintain domain specificity and minimize data contamination, the research examines the models’ performance in these two tasks. Our findings reveal the nuanced capabilities of LLMs in handling MTPE and MQM tasks, hinting at the potential of these models in streamlining and optimizing translation workflows. Future directions include fine-tuning LLMs for task-specific improvements and exploring the integration of style guides for enhanced translation quality.
%U https://aclanthology.org/2024.eamt-1.32
%P 373-386
Markdown (Informal)
[LLMs in Post-Translation Workflows: Comparing Performance in Post-Editing and Error Analysis](https://aclanthology.org/2024.eamt-1.32) (Uguet et al., EAMT 2024)
ACL