@inproceedings{ben-kheder-etal-2024-aladan,
title = "{ALADAN} at {IWSLT}24 Low-resource {A}rabic Dialectal Speech Translation Task",
author = "Ben Kheder, Waad and
Jon, Josef and
Beyer, Andr{\'e} and
Messaoudi, Abdel and
Affan, Rabea and
Barras, Claude and
Tychonov, Maxim and
Gauvain, Jean-Luc",
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-1.25/",
doi = "10.18653/v1/2024.iwslt-1.25",
pages = "192--202",
abstract = "This paper presents ALADAN`s approach to the IWSLT 2024 Dialectal and Low-resource shared task, focusing on Levantine Arabic (apc) and Tunisian Arabic (aeb) to English speech translation (ST). Addressing challenges such as the lack of standardized orthography and limited training data, we propose a solution for data normalization in Dialectal Arabic, employing a modified Levenshtein distance and Word2vec models to find orthographic variants of the same word. Our system consists of a cascade ST system integrating two ASR systems (TDNN-F and Zipformer) and two NMT modules derived from pre-trained models (NLLB-200 1.3B distilled model and CohereAI`s Command-R). Additionally, we explore the integration of unsupervised textual and audio data, highlighting the importance of multi-dialectal datasets for both ASR and NMT tasks. Our system achieves BLEU score of 31.5 for Levantine Arabic on the official validation set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ben-kheder-etal-2024-aladan">
<titleInfo>
<title>ALADAN at IWSLT24 Low-resource Arabic Dialectal Speech Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Waad</namePart>
<namePart type="family">Ben Kheder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Jon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Beyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdel</namePart>
<namePart type="family">Messaoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rabea</namePart>
<namePart type="family">Affan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claude</namePart>
<namePart type="family">Barras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Tychonov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Luc</namePart>
<namePart type="family">Gauvain</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>This paper presents ALADAN‘s approach to the IWSLT 2024 Dialectal and Low-resource shared task, focusing on Levantine Arabic (apc) and Tunisian Arabic (aeb) to English speech translation (ST). Addressing challenges such as the lack of standardized orthography and limited training data, we propose a solution for data normalization in Dialectal Arabic, employing a modified Levenshtein distance and Word2vec models to find orthographic variants of the same word. Our system consists of a cascade ST system integrating two ASR systems (TDNN-F and Zipformer) and two NMT modules derived from pre-trained models (NLLB-200 1.3B distilled model and CohereAI‘s Command-R). Additionally, we explore the integration of unsupervised textual and audio data, highlighting the importance of multi-dialectal datasets for both ASR and NMT tasks. Our system achieves BLEU score of 31.5 for Levantine Arabic on the official validation set.</abstract>
<identifier type="citekey">ben-kheder-etal-2024-aladan</identifier>
<identifier type="doi">10.18653/v1/2024.iwslt-1.25</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.25/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>192</start>
<end>202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ALADAN at IWSLT24 Low-resource Arabic Dialectal Speech Translation Task
%A Ben Kheder, Waad
%A Jon, Josef
%A Beyer, André
%A Messaoudi, Abdel
%A Affan, Rabea
%A Barras, Claude
%A Tychonov, Maxim
%A Gauvain, Jean-Luc
%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 ben-kheder-etal-2024-aladan
%X This paper presents ALADAN‘s approach to the IWSLT 2024 Dialectal and Low-resource shared task, focusing on Levantine Arabic (apc) and Tunisian Arabic (aeb) to English speech translation (ST). Addressing challenges such as the lack of standardized orthography and limited training data, we propose a solution for data normalization in Dialectal Arabic, employing a modified Levenshtein distance and Word2vec models to find orthographic variants of the same word. Our system consists of a cascade ST system integrating two ASR systems (TDNN-F and Zipformer) and two NMT modules derived from pre-trained models (NLLB-200 1.3B distilled model and CohereAI‘s Command-R). Additionally, we explore the integration of unsupervised textual and audio data, highlighting the importance of multi-dialectal datasets for both ASR and NMT tasks. Our system achieves BLEU score of 31.5 for Levantine Arabic on the official validation set.
%R 10.18653/v1/2024.iwslt-1.25
%U https://aclanthology.org/2024.iwslt-1.25/
%U https://doi.org/10.18653/v1/2024.iwslt-1.25
%P 192-202
Markdown (Informal)
[ALADAN at IWSLT24 Low-resource Arabic Dialectal Speech Translation Task](https://aclanthology.org/2024.iwslt-1.25/) (Ben Kheder et al., IWSLT 2024)
ACL
- Waad Ben Kheder, Josef Jon, André Beyer, Abdel Messaoudi, Rabea Affan, Claude Barras, Maxim Tychonov, and Jean-Luc Gauvain. 2024. ALADAN at IWSLT24 Low-resource Arabic Dialectal Speech Translation Task. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 192–202, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.