@inproceedings{fares-touileb-2024-babelbot,
title = "{B}abel{B}ot at {A}ra{F}in{NLP}2024: Fine-tuning T5 for Multi-dialect Intent Detection with Synthetic Data and Model Ensembling",
author = "Fares, Murhaf and
Touileb, Samia",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.40",
pages = "433--440",
abstract = "This paper presents our results for the Arabic Financial NLP (AraFinNLP) shared task at the Second Arabic Natural Language Processing Conference (ArabicNLP 2024). We participated in the first sub-task, Multi-dialect Intent Detection, which focused on cross-dialect intent detection in the banking domain. Our approach involved fine-tuning an encoder-only T5 model, generating synthetic data, and model ensembling. Additionally, we conducted an in-depth analysis of the dataset, addressing annotation errors and problematic translations. Our model was ranked third in the shared task, achieving a F1-score of 0.871.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fares-touileb-2024-babelbot">
<titleInfo>
<title>BabelBot at AraFinNLP2024: Fine-tuning T5 for Multi-dialect Intent Detection with Synthetic Data and Model Ensembling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Murhaf</namePart>
<namePart type="family">Fares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</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 Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our results for the Arabic Financial NLP (AraFinNLP) shared task at the Second Arabic Natural Language Processing Conference (ArabicNLP 2024). We participated in the first sub-task, Multi-dialect Intent Detection, which focused on cross-dialect intent detection in the banking domain. Our approach involved fine-tuning an encoder-only T5 model, generating synthetic data, and model ensembling. Additionally, we conducted an in-depth analysis of the dataset, addressing annotation errors and problematic translations. Our model was ranked third in the shared task, achieving a F1-score of 0.871.</abstract>
<identifier type="citekey">fares-touileb-2024-babelbot</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.40</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>433</start>
<end>440</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BabelBot at AraFinNLP2024: Fine-tuning T5 for Multi-dialect Intent Detection with Synthetic Data and Model Ensembling
%A Fares, Murhaf
%A Touileb, Samia
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of The Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F fares-touileb-2024-babelbot
%X This paper presents our results for the Arabic Financial NLP (AraFinNLP) shared task at the Second Arabic Natural Language Processing Conference (ArabicNLP 2024). We participated in the first sub-task, Multi-dialect Intent Detection, which focused on cross-dialect intent detection in the banking domain. Our approach involved fine-tuning an encoder-only T5 model, generating synthetic data, and model ensembling. Additionally, we conducted an in-depth analysis of the dataset, addressing annotation errors and problematic translations. Our model was ranked third in the shared task, achieving a F1-score of 0.871.
%U https://aclanthology.org/2024.arabicnlp-1.40
%P 433-440
Markdown (Informal)
[BabelBot at AraFinNLP2024: Fine-tuning T5 for Multi-dialect Intent Detection with Synthetic Data and Model Ensembling](https://aclanthology.org/2024.arabicnlp-1.40) (Fares & Touileb, ArabicNLP-WS 2024)
ACL