@inproceedings{gaona-etal-2026-fuzzy,
title = "Fuzzy Matching and Sentence Embeddings for Few-shot Machine Translation with Large Language Models",
author = "Gaona, Miguel Angel Rios and
Plieseis, Claudia and
Ciobanu, Dragos and
Secara, Alina",
editor = "Shterionov, Dimitar and
Vanmassenhove, Eva and
De Sisto, Mirella and
Blain, Fred and
Pourmostafa Roshan Sharami, Javad and
Lepp, Lisa and
Manna, Chiara and
Rescigno, Argentina Anna and
Karakanta, Alina and
Rigouts Terryn, Ayla and
Lardelli, Manuel and
Resende, Natalia and
Murgolo, Elena and
Hackenbuchner, Jani{\c{c}}a and
Zaretskaya, Anna and
Espl{\`a}-Gomis, Miquel and
Etchegoyhen, Thierry and
Gromann, Dagmar and
Bawden, Rachel and
Haddow, Barry and
Szoc, Sara and
Forcada, Mikel and
Moniz, Helena",
booktitle = "Proceedings of the 26th Annual Conference of the {E}uropean Association for Machine Translation (Volume 1)",
month = jun,
year = "2026",
address = "Tilburg, The Netherlands",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2026.eamt-1.34/",
pages = "538--550",
ISBN = "9789403901411",
abstract = "In-context learning is a method for improving machine translation in Large Language Models, but its performance is sensitive to the quality of the few-shot example selection. Current retrieval strategies use semantic similarity by computing sentence embeddings, and these methods often require significant computational overhead and specialised expertise. We evaluate the impact of retrieval strategies on translation performance in a specialised domain, comparing traditional, token-based fuzzy matching against semantic sentence embeddings. We use a medical corpus from the European Medicines Agency (EMEA) for the English-Romanian and English-German language pairs, and we evaluate translation quality with automatic metrics and manual evaluation. Our results show that 1-shot and 5-shot prompting significantly outperforms the 0-shot baselines for quality in automatic evaluations for both language pairs, and in manual evaluation for English-German. For the English-Romanian pair, the average scores of the manual evaluation for both quality and ranking follow the same trend, but with no statistical significance. Token-based fuzzy matching overwhelmingly has higher automatic quality scores than embedding-based retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaona-etal-2026-fuzzy">
<titleInfo>
<title>Fuzzy Matching and Sentence Embeddings for Few-shot Machine Translation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Angel</namePart>
<namePart type="given">Rios</namePart>
<namePart type="family">Gaona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Plieseis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragos</namePart>
<namePart type="family">Ciobanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Secara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">De Sisto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Blain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="family">Pourmostafa Roshan Sharami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Lepp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiara</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Argentina</namePart>
<namePart type="given">Anna</namePart>
<namePart type="family">Rescigno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="family">Rigouts Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Lardelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Resende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Murgolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janiça</namePart>
<namePart type="family">Hackenbuchner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Zaretskaya</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>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Etchegoyhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</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">Barry</namePart>
<namePart type="family">Haddow</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>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</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</publisher>
<place>
<placeTerm type="text">Tilburg, The Netherlands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">9789403901411</identifier>
</relatedItem>
<abstract>In-context learning is a method for improving machine translation in Large Language Models, but its performance is sensitive to the quality of the few-shot example selection. Current retrieval strategies use semantic similarity by computing sentence embeddings, and these methods often require significant computational overhead and specialised expertise. We evaluate the impact of retrieval strategies on translation performance in a specialised domain, comparing traditional, token-based fuzzy matching against semantic sentence embeddings. We use a medical corpus from the European Medicines Agency (EMEA) for the English-Romanian and English-German language pairs, and we evaluate translation quality with automatic metrics and manual evaluation. Our results show that 1-shot and 5-shot prompting significantly outperforms the 0-shot baselines for quality in automatic evaluations for both language pairs, and in manual evaluation for English-German. For the English-Romanian pair, the average scores of the manual evaluation for both quality and ranking follow the same trend, but with no statistical significance. Token-based fuzzy matching overwhelmingly has higher automatic quality scores than embedding-based retrieval.</abstract>
<identifier type="citekey">gaona-etal-2026-fuzzy</identifier>
<location>
<url>https://aclanthology.org/2026.eamt-1.34/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>538</start>
<end>550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fuzzy Matching and Sentence Embeddings for Few-shot Machine Translation with Large Language Models
%A Gaona, Miguel Angel Rios
%A Plieseis, Claudia
%A Ciobanu, Dragos
%A Secara, Alina
%Y Shterionov, Dimitar
%Y Vanmassenhove, Eva
%Y De Sisto, Mirella
%Y Blain, Fred
%Y Pourmostafa Roshan Sharami, Javad
%Y Lepp, Lisa
%Y Manna, Chiara
%Y Rescigno, Argentina Anna
%Y Karakanta, Alina
%Y Rigouts Terryn, Ayla
%Y Lardelli, Manuel
%Y Resende, Natalia
%Y Murgolo, Elena
%Y Hackenbuchner, Janiça
%Y Zaretskaya, Anna
%Y Esplà-Gomis, Miquel
%Y Etchegoyhen, Thierry
%Y Gromann, Dagmar
%Y Bawden, Rachel
%Y Haddow, Barry
%Y Szoc, Sara
%Y Forcada, Mikel
%Y Moniz, Helena
%S Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2026
%8 June
%I European Association for Machine Translation
%C Tilburg, The Netherlands
%@ 9789403901411
%F gaona-etal-2026-fuzzy
%X In-context learning is a method for improving machine translation in Large Language Models, but its performance is sensitive to the quality of the few-shot example selection. Current retrieval strategies use semantic similarity by computing sentence embeddings, and these methods often require significant computational overhead and specialised expertise. We evaluate the impact of retrieval strategies on translation performance in a specialised domain, comparing traditional, token-based fuzzy matching against semantic sentence embeddings. We use a medical corpus from the European Medicines Agency (EMEA) for the English-Romanian and English-German language pairs, and we evaluate translation quality with automatic metrics and manual evaluation. Our results show that 1-shot and 5-shot prompting significantly outperforms the 0-shot baselines for quality in automatic evaluations for both language pairs, and in manual evaluation for English-German. For the English-Romanian pair, the average scores of the manual evaluation for both quality and ranking follow the same trend, but with no statistical significance. Token-based fuzzy matching overwhelmingly has higher automatic quality scores than embedding-based retrieval.
%U https://aclanthology.org/2026.eamt-1.34/
%P 538-550
Markdown (Informal)
[Fuzzy Matching and Sentence Embeddings for Few-shot Machine Translation with Large Language Models](https://aclanthology.org/2026.eamt-1.34/) (Gaona et al., EAMT 2026)
ACL