@inproceedings{suwaileh-etal-2023-idrisi-arabic,
title = "{IDRISI}-{D}: {A}rabic and {E}nglish Datasets and Benchmarks for Location Mention Disambiguation over Disaster Microblogs",
author = "Suwaileh, Reem and
Elsayed, Tamer and
Imran, Muhammad",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.14",
doi = "10.18653/v1/2023.arabicnlp-1.14",
pages = "158--169",
abstract = "Extracting and disambiguating geolocation information from social media data enables effective disaster management, as it helps response authorities; for example, locating incidents for planning rescue activities and affected people for evacuation. Nevertheless, the dearth of resources and tools hinders the development and evaluation of Location Mention Disambiguation (LMD) models in the disaster management domain. Consequently, the LMD task is greatly understudied, especially for the low resource languages such as Arabic. To fill this gap, we introduce IDRISI-D, the largest to date English and the first Arabic public LMD datasets. Additionally, we introduce a modified hierarchical evaluation framework that offers a lenient and nuanced evaluation of LMD systems. We further benchmark IDRISI-D datasets using representative baselines and show the competitiveness of BERT-based models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suwaileh-etal-2023-idrisi-arabic">
<titleInfo>
<title>IDRISI-D: Arabic and English Datasets and Benchmarks for Location Mention Disambiguation over Disaster Microblogs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Suwaileh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Imran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</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">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">Nizar</namePart>
<namePart type="family">Habash</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">Amr</namePart>
<namePart type="family">Keleg</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">Khalil</namePart>
<namePart type="family">Mrini</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extracting and disambiguating geolocation information from social media data enables effective disaster management, as it helps response authorities; for example, locating incidents for planning rescue activities and affected people for evacuation. Nevertheless, the dearth of resources and tools hinders the development and evaluation of Location Mention Disambiguation (LMD) models in the disaster management domain. Consequently, the LMD task is greatly understudied, especially for the low resource languages such as Arabic. To fill this gap, we introduce IDRISI-D, the largest to date English and the first Arabic public LMD datasets. Additionally, we introduce a modified hierarchical evaluation framework that offers a lenient and nuanced evaluation of LMD systems. We further benchmark IDRISI-D datasets using representative baselines and show the competitiveness of BERT-based models.</abstract>
<identifier type="citekey">suwaileh-etal-2023-idrisi-arabic</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.14</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.14</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>158</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IDRISI-D: Arabic and English Datasets and Benchmarks for Location Mention Disambiguation over Disaster Microblogs
%A Suwaileh, Reem
%A Elsayed, Tamer
%A Imran, Muhammad
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F suwaileh-etal-2023-idrisi-arabic
%X Extracting and disambiguating geolocation information from social media data enables effective disaster management, as it helps response authorities; for example, locating incidents for planning rescue activities and affected people for evacuation. Nevertheless, the dearth of resources and tools hinders the development and evaluation of Location Mention Disambiguation (LMD) models in the disaster management domain. Consequently, the LMD task is greatly understudied, especially for the low resource languages such as Arabic. To fill this gap, we introduce IDRISI-D, the largest to date English and the first Arabic public LMD datasets. Additionally, we introduce a modified hierarchical evaluation framework that offers a lenient and nuanced evaluation of LMD systems. We further benchmark IDRISI-D datasets using representative baselines and show the competitiveness of BERT-based models.
%R 10.18653/v1/2023.arabicnlp-1.14
%U https://aclanthology.org/2023.arabicnlp-1.14
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.14
%P 158-169
Markdown (Informal)
[IDRISI-D: Arabic and English Datasets and Benchmarks for Location Mention Disambiguation over Disaster Microblogs](https://aclanthology.org/2023.arabicnlp-1.14) (Suwaileh et al., ArabicNLP-WS 2023)
ACL