@inproceedings{hu-etal-2024-learning,
title = "Learning from Wrong Predictions in Low-Resource Neural Machine Translation",
author = "Hu, Jia Cheng and
Cavicchioli, Roberto and
Berardinelli, Giulia and
Capotondi, Alessandro",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.896",
pages = "10263--10273",
abstract = "Resource scarcity in Neural Machine Translation is a challenging problem in both industry applications and in the support of less-spoken languages represented, in the worst case, by endangered and low-resource languages. Many Data Augmentation methods rely on additional linguistic sources and software tools but these are often not available in less favoured language. For this reason, we present USKI (Unaligned Sentences Keytokens pre-traIning), a pre-training strategy that leverages the relationships and similarities that exist between unaligned sentences. By doing so, we increase the dataset size of endangered and low-resource languages by the square of the initial quantity, matching the typical size of high-resource language datasets such as WMT14 En-Fr. Results showcase the effectiveness of our approach with an increase on average of 0.9 BLEU across the benchmarks using a small fraction of the entire unaligned corpus, suggesting the importance of the research topic and the potential of a currently under-utilized resource and under-explored approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2024-learning">
<titleInfo>
<title>Learning from Wrong Predictions in Low-Resource Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="given">Cheng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Cavicchioli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Berardinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Capotondi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Resource scarcity in Neural Machine Translation is a challenging problem in both industry applications and in the support of less-spoken languages represented, in the worst case, by endangered and low-resource languages. Many Data Augmentation methods rely on additional linguistic sources and software tools but these are often not available in less favoured language. For this reason, we present USKI (Unaligned Sentences Keytokens pre-traIning), a pre-training strategy that leverages the relationships and similarities that exist between unaligned sentences. By doing so, we increase the dataset size of endangered and low-resource languages by the square of the initial quantity, matching the typical size of high-resource language datasets such as WMT14 En-Fr. Results showcase the effectiveness of our approach with an increase on average of 0.9 BLEU across the benchmarks using a small fraction of the entire unaligned corpus, suggesting the importance of the research topic and the potential of a currently under-utilized resource and under-explored approach.</abstract>
<identifier type="citekey">hu-etal-2024-learning</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.896</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10263</start>
<end>10273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning from Wrong Predictions in Low-Resource Neural Machine Translation
%A Hu, Jia Cheng
%A Cavicchioli, Roberto
%A Berardinelli, Giulia
%A Capotondi, Alessandro
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F hu-etal-2024-learning
%X Resource scarcity in Neural Machine Translation is a challenging problem in both industry applications and in the support of less-spoken languages represented, in the worst case, by endangered and low-resource languages. Many Data Augmentation methods rely on additional linguistic sources and software tools but these are often not available in less favoured language. For this reason, we present USKI (Unaligned Sentences Keytokens pre-traIning), a pre-training strategy that leverages the relationships and similarities that exist between unaligned sentences. By doing so, we increase the dataset size of endangered and low-resource languages by the square of the initial quantity, matching the typical size of high-resource language datasets such as WMT14 En-Fr. Results showcase the effectiveness of our approach with an increase on average of 0.9 BLEU across the benchmarks using a small fraction of the entire unaligned corpus, suggesting the importance of the research topic and the potential of a currently under-utilized resource and under-explored approach.
%U https://aclanthology.org/2024.lrec-main.896
%P 10263-10273
Markdown (Informal)
[Learning from Wrong Predictions in Low-Resource Neural Machine Translation](https://aclanthology.org/2024.lrec-main.896) (Hu et al., LREC-COLING 2024)
ACL