@inproceedings{nieminen-2024-adding,
title = "Adding soft terminology constraints to pre-trained generic {MT} models by means of continued training",
author = "Nieminen, Tommi",
editor = "Tezcan, Arda and
S{\'a}nchez-Cartagena, V{\'\i}ctor M. and
Espl{\`a}-Gomis, Miquel",
booktitle = "Proceedings of the First International Workshop on Knowledge-Enhanced Machine Translation",
month = jun,
year = "2024",
address = "Sheffield, United Kingdom",
publisher = "European Association for Machine Translation (EAMT)",
url = "https://aclanthology.org/2024.kemt-1.3",
pages = "21--33",
abstract = "This article describes an efficient method of adding terminology support to existing machine translation models. The training of the pre-trained models is continued with parallel data where strings identified as terms in the source language data have been annotated with the lemmas of the corresponding target terms. Evaluation using standard test sets and methods confirms that continued training from generic base models can produce term models that are competitive with models specifically trained as term models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nieminen-2024-adding">
<titleInfo>
<title>Adding soft terminology constraints to pre-trained generic MT models by means of continued training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Nieminen</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 First International Workshop on Knowledge-Enhanced Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Tezcan</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">Miquel</namePart>
<namePart type="family">Esplà-Gomis</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, United Kingdom</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes an efficient method of adding terminology support to existing machine translation models. The training of the pre-trained models is continued with parallel data where strings identified as terms in the source language data have been annotated with the lemmas of the corresponding target terms. Evaluation using standard test sets and methods confirms that continued training from generic base models can produce term models that are competitive with models specifically trained as term models.</abstract>
<identifier type="citekey">nieminen-2024-adding</identifier>
<location>
<url>https://aclanthology.org/2024.kemt-1.3</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>21</start>
<end>33</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adding soft terminology constraints to pre-trained generic MT models by means of continued training
%A Nieminen, Tommi
%Y Tezcan, Arda
%Y Sánchez-Cartagena, Víctor M.
%Y Esplà-Gomis, Miquel
%S Proceedings of the First International Workshop on Knowledge-Enhanced Machine Translation
%D 2024
%8 June
%I European Association for Machine Translation (EAMT)
%C Sheffield, United Kingdom
%F nieminen-2024-adding
%X This article describes an efficient method of adding terminology support to existing machine translation models. The training of the pre-trained models is continued with parallel data where strings identified as terms in the source language data have been annotated with the lemmas of the corresponding target terms. Evaluation using standard test sets and methods confirms that continued training from generic base models can produce term models that are competitive with models specifically trained as term models.
%U https://aclanthology.org/2024.kemt-1.3
%P 21-33
Markdown (Informal)
[Adding soft terminology constraints to pre-trained generic MT models by means of continued training](https://aclanthology.org/2024.kemt-1.3) (Nieminen, KEMT-WS 2024)
ACL