@inproceedings{f1d2abd14b33432c80a63c393c7be1ed,
title = "IDRISI-D: Arabic and English Datasets and Benchmarks for Location Mention Disambiguation over Disaster Microblogs",
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.",
author = "Reem Suwaileh and Tamer Elsayed and Muhammad Imran",
note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 1st Arabic Natural Language Processing Conference, ArabicNLP 2023 ; Conference date: 07-12-2023",
year = "2023",
doi = "10.18653/v1/2023.arabicnlp-1.14",
language = "English",
series = "ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "158--169",
editor = "Hassan Sawaf and Samhaa El-Beltagy and Wajdi Zaghouani and Walid Magdy and Nadi Tomeh and {Abu Farha}, Ibrahim and Nizar Habash and Salam Khalifa and Amr Keleg and Hatem Haddad and Imed Zitouni and Ahmed Abdelali and Khalil Mrini and Rawan Almatham",
booktitle = "ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Porceedings",
address = "United States",
}