@inproceedings{ibrahim-2025-cufe,
title = "{CUFE}@{V}ar{D}ial 2025 {N}or{SID}: Multilingual {BERT} for {N}orwegian Dialect Identification and Intent Detection",
author = "Ibrahim, Michael",
editor = "Scherrer, Yves and
Jauhiainen, Tommi and
Ljube{\v{s}}i{\'c}, Nikola and
Nakov, Preslav and
Tiedemann, Jorg and
Zampieri, Marcos",
booktitle = "Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.vardial-1.17/",
pages = "220--223",
abstract = "Dialect identification is crucial in enhancing various tasks, including sentiment analysis, as a speaker`s geographical origin can significantly affect their perspective on a topic, also, intent detection has gained significant traction in natural language processing due to its applications in various domains, including virtual assistants, customer service automation, and information retrieval systems. This work describes a system developed for VarDial 2025: Norwegian slot and intent detection and dialect identification shared task (Scherrer et al., 2025), a challenge designed to address the dialect recognition and intent detection problems for a low-resource language like Norwegian. More specifically, this work investigates the performance of different BERT models in solving this problem. Finally, the output of the multilingual version of the BERT model was submitted to this shared task, the developed system achieved a weighted F1 score of 79.64 for dialect identification and an accuracy of 94.38 for intent detection."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ibrahim-2025-cufe">
<titleInfo>
<title>CUFE@VarDial 2025 NorSID: Multilingual BERT for Norwegian Dialect Identification and Intent Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Ibrahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialect identification is crucial in enhancing various tasks, including sentiment analysis, as a speaker‘s geographical origin can significantly affect their perspective on a topic, also, intent detection has gained significant traction in natural language processing due to its applications in various domains, including virtual assistants, customer service automation, and information retrieval systems. This work describes a system developed for VarDial 2025: Norwegian slot and intent detection and dialect identification shared task (Scherrer et al., 2025), a challenge designed to address the dialect recognition and intent detection problems for a low-resource language like Norwegian. More specifically, this work investigates the performance of different BERT models in solving this problem. Finally, the output of the multilingual version of the BERT model was submitted to this shared task, the developed system achieved a weighted F1 score of 79.64 for dialect identification and an accuracy of 94.38 for intent detection.</abstract>
<identifier type="citekey">ibrahim-2025-cufe</identifier>
<location>
<url>https://aclanthology.org/2025.vardial-1.17/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>220</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUFE@VarDial 2025 NorSID: Multilingual BERT for Norwegian Dialect Identification and Intent Detection
%A Ibrahim, Michael
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Nakov, Preslav
%Y Tiedemann, Jorg
%Y Zampieri, Marcos
%S Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F ibrahim-2025-cufe
%X Dialect identification is crucial in enhancing various tasks, including sentiment analysis, as a speaker‘s geographical origin can significantly affect their perspective on a topic, also, intent detection has gained significant traction in natural language processing due to its applications in various domains, including virtual assistants, customer service automation, and information retrieval systems. This work describes a system developed for VarDial 2025: Norwegian slot and intent detection and dialect identification shared task (Scherrer et al., 2025), a challenge designed to address the dialect recognition and intent detection problems for a low-resource language like Norwegian. More specifically, this work investigates the performance of different BERT models in solving this problem. Finally, the output of the multilingual version of the BERT model was submitted to this shared task, the developed system achieved a weighted F1 score of 79.64 for dialect identification and an accuracy of 94.38 for intent detection.
%U https://aclanthology.org/2025.vardial-1.17/
%P 220-223
Markdown (Informal)
[CUFE@VarDial 2025 NorSID: Multilingual BERT for Norwegian Dialect Identification and Intent Detection](https://aclanthology.org/2025.vardial-1.17/) (Ibrahim, VarDial 2025)
ACL