@inproceedings{eschbach-dymanus-etal-2024-exploring,
title = "Exploring the Effectiveness of {LLM} Domain Adaptation for Business {IT} Machine Translation",
author = "Eschbach-Dymanus, Johannes and
Essenberger, Frank and
Buschbeck, Bianka and
Exel, Miriam",
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-1.51",
pages = "610--622",
abstract = "In this paper, we study the translation abilities of Large Language Models (LLMs) for business IT texts.We are strongly interested in domain adaptation of translation systems, which is essential for accurate and lexically appropriate translation of such texts.Among the open-source models evaluated in a zero- and few-shot setting, we find Llama-2 13B the most promising for domain-specific translation fine-tuning.We investigate the full range of adaptation techniques for LLMs: from prompting, over parameter-efficient fine-tuning to full fine-tuning, and compare to classic neural machine translation (MT) models trained internally at SAP.We provide guidance how to use training budget most effectively for different fine-tuning approaches.We observe that while LLMs can translate on-par with SAP{'}s MT models on general domain data, it is difficult to close the gap on SAP{'}s domain-specific data, even with extensive training and carefully curated data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eschbach-dymanus-etal-2024-exploring">
<titleInfo>
<title>Exploring the Effectiveness of LLM Domain Adaptation for Business IT Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Eschbach-Dymanus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Essenberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bianka</namePart>
<namePart type="family">Buschbeck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Exel</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>In this paper, we study the translation abilities of Large Language Models (LLMs) for business IT texts.We are strongly interested in domain adaptation of translation systems, which is essential for accurate and lexically appropriate translation of such texts.Among the open-source models evaluated in a zero- and few-shot setting, we find Llama-2 13B the most promising for domain-specific translation fine-tuning.We investigate the full range of adaptation techniques for LLMs: from prompting, over parameter-efficient fine-tuning to full fine-tuning, and compare to classic neural machine translation (MT) models trained internally at SAP.We provide guidance how to use training budget most effectively for different fine-tuning approaches.We observe that while LLMs can translate on-par with SAP’s MT models on general domain data, it is difficult to close the gap on SAP’s domain-specific data, even with extensive training and carefully curated data.</abstract>
<identifier type="citekey">eschbach-dymanus-etal-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.eamt-1.51</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>610</start>
<end>622</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Effectiveness of LLM Domain Adaptation for Business IT Machine Translation
%A Eschbach-Dymanus, Johannes
%A Essenberger, Frank
%A Buschbeck, Bianka
%A Exel, Miriam
%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 eschbach-dymanus-etal-2024-exploring
%X In this paper, we study the translation abilities of Large Language Models (LLMs) for business IT texts.We are strongly interested in domain adaptation of translation systems, which is essential for accurate and lexically appropriate translation of such texts.Among the open-source models evaluated in a zero- and few-shot setting, we find Llama-2 13B the most promising for domain-specific translation fine-tuning.We investigate the full range of adaptation techniques for LLMs: from prompting, over parameter-efficient fine-tuning to full fine-tuning, and compare to classic neural machine translation (MT) models trained internally at SAP.We provide guidance how to use training budget most effectively for different fine-tuning approaches.We observe that while LLMs can translate on-par with SAP’s MT models on general domain data, it is difficult to close the gap on SAP’s domain-specific data, even with extensive training and carefully curated data.
%U https://aclanthology.org/2024.eamt-1.51
%P 610-622
Markdown (Informal)
[Exploring the Effectiveness of LLM Domain Adaptation for Business IT Machine Translation](https://aclanthology.org/2024.eamt-1.51) (Eschbach-Dymanus et al., EAMT 2024)
ACL