@inproceedings{nabhani-etal-2024-um,
title = "{UM} {IWSLT} 2024 Low-Resource Speech Translation: Combining {M}altese and {N}orth {L}evantine {A}rabic",
author = "Nabhani, Sara and
Williams, Aiden and
Jannat, Miftahul and
Rebecca Belcher, Kate and
Galea, Melanie and
Taylor, Anna and
Micallef, Kurt and
Borg, Claudia",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwslt-1.14",
pages = "97--107",
abstract = "The IWSLT low-resource track encourages innovation in the field of speech translation, particularly in data-scarce conditions. This paper details our submission for the IWSLT 2024 low-resource track shared task for Maltese-English and North Levantine Arabic-English spoken language translation using an unconstrained pipeline approach. Using language models, we improve ASR performance by correcting the produced output. We present a 2 step approach for MT using data from external sources showing improvements over baseline systems. We also explore transliteration as a means to further augment MT data and exploit the cross-lingual similarities between Maltese and Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nabhani-etal-2024-um">
<titleInfo>
<title>UM IWSLT 2024 Low-Resource Speech Translation: Combining Maltese and North Levantine Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Nabhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiden</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miftahul</namePart>
<namePart type="family">Jannat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kate</namePart>
<namePart type="family">Rebecca Belcher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Galea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurt</namePart>
<namePart type="family">Micallef</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Borg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The IWSLT low-resource track encourages innovation in the field of speech translation, particularly in data-scarce conditions. This paper details our submission for the IWSLT 2024 low-resource track shared task for Maltese-English and North Levantine Arabic-English spoken language translation using an unconstrained pipeline approach. Using language models, we improve ASR performance by correcting the produced output. We present a 2 step approach for MT using data from external sources showing improvements over baseline systems. We also explore transliteration as a means to further augment MT data and exploit the cross-lingual similarities between Maltese and Arabic.</abstract>
<identifier type="citekey">nabhani-etal-2024-um</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.14</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>97</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UM IWSLT 2024 Low-Resource Speech Translation: Combining Maltese and North Levantine Arabic
%A Nabhani, Sara
%A Williams, Aiden
%A Jannat, Miftahul
%A Rebecca Belcher, Kate
%A Galea, Melanie
%A Taylor, Anna
%A Micallef, Kurt
%A Borg, Claudia
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F nabhani-etal-2024-um
%X The IWSLT low-resource track encourages innovation in the field of speech translation, particularly in data-scarce conditions. This paper details our submission for the IWSLT 2024 low-resource track shared task for Maltese-English and North Levantine Arabic-English spoken language translation using an unconstrained pipeline approach. Using language models, we improve ASR performance by correcting the produced output. We present a 2 step approach for MT using data from external sources showing improvements over baseline systems. We also explore transliteration as a means to further augment MT data and exploit the cross-lingual similarities between Maltese and Arabic.
%U https://aclanthology.org/2024.iwslt-1.14
%P 97-107
Markdown (Informal)
[UM IWSLT 2024 Low-Resource Speech Translation: Combining Maltese and North Levantine Arabic](https://aclanthology.org/2024.iwslt-1.14) (Nabhani et al., IWSLT 2024)
ACL
- Sara Nabhani, Aiden Williams, Miftahul Jannat, Kate Rebecca Belcher, Melanie Galea, Anna Taylor, Kurt Micallef, and Claudia Borg. 2024. UM IWSLT 2024 Low-Resource Speech Translation: Combining Maltese and North Levantine Arabic. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 97–107, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.