@inproceedings{aulamo-etal-2026-challenge,
title = "The Challenge of Finding Robust and Efficient Strategies for Training Machine Translation Models with Noisy Data",
author = {Aulamo, Mikko and
Virpioja, Sami and
Scherrer, Yves and
Tiedemann, J{\"o}rg},
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-1.13/",
pages = "158--172",
ISBN = "9789403901411",
abstract = "Most machine translation datasets come with a certain level of noise, and strategies for handling such data need to be robust and efficient. Data selection and filtering are challenging and may depend on expensive language-specific tools that are not necessarily available, especially for low-resource languages. This paper looks at training strategies that combine cheap heuristic filters with curriculum learning to implement iterative procedures that robustly operate on raw noisy data without expensive prior preprocessing and data selection. The intuition is that we can cluster data into buckets with varying noise levels and use different sets of buckets at different stages of MT model training. We test various strategies and compare them to pre-filtering approaches for a diverse set of low-resource languages and conclude that curriculum learning can improve robustness but does not necessarily lead to improved translation performance. Overall, the experiments demonstrate the importance of proper experimental workflows, which cannot easily generalize from one language pair and scenario to another."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aulamo-etal-2026-challenge">
<titleInfo>
<title>The Challenge of Finding Robust and Efficient Strategies for Training Machine Translation Models with Noisy Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Aulamo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sami</namePart>
<namePart type="family">Virpioja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</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>Most machine translation datasets come with a certain level of noise, and strategies for handling such data need to be robust and efficient. Data selection and filtering are challenging and may depend on expensive language-specific tools that are not necessarily available, especially for low-resource languages. This paper looks at training strategies that combine cheap heuristic filters with curriculum learning to implement iterative procedures that robustly operate on raw noisy data without expensive prior preprocessing and data selection. The intuition is that we can cluster data into buckets with varying noise levels and use different sets of buckets at different stages of MT model training. We test various strategies and compare them to pre-filtering approaches for a diverse set of low-resource languages and conclude that curriculum learning can improve robustness but does not necessarily lead to improved translation performance. Overall, the experiments demonstrate the importance of proper experimental workflows, which cannot easily generalize from one language pair and scenario to another.</abstract>
<identifier type="citekey">aulamo-etal-2026-challenge</identifier>
<location>
<url>https://aclanthology.org/2026.eamt-1.13/</url>
</location>
<part>
<date>2026-06</date>
<extent unit="page">
<start>158</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Challenge of Finding Robust and Efficient Strategies for Training Machine Translation Models with Noisy Data
%A Aulamo, Mikko
%A Virpioja, Sami
%A Scherrer, Yves
%A Tiedemann, Jörg
%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 aulamo-etal-2026-challenge
%X Most machine translation datasets come with a certain level of noise, and strategies for handling such data need to be robust and efficient. Data selection and filtering are challenging and may depend on expensive language-specific tools that are not necessarily available, especially for low-resource languages. This paper looks at training strategies that combine cheap heuristic filters with curriculum learning to implement iterative procedures that robustly operate on raw noisy data without expensive prior preprocessing and data selection. The intuition is that we can cluster data into buckets with varying noise levels and use different sets of buckets at different stages of MT model training. We test various strategies and compare them to pre-filtering approaches for a diverse set of low-resource languages and conclude that curriculum learning can improve robustness but does not necessarily lead to improved translation performance. Overall, the experiments demonstrate the importance of proper experimental workflows, which cannot easily generalize from one language pair and scenario to another.
%U https://aclanthology.org/2026.eamt-1.13/
%P 158-172
Markdown (Informal)
[The Challenge of Finding Robust and Efficient Strategies for Training Machine Translation Models with Noisy Data](https://aclanthology.org/2026.eamt-1.13/) (Aulamo et al., EAMT 2026)
ACL