Show simple item record

AuthorSuwaileh, Reem
AuthorImran, Muhammad
AuthorElsayed, Tamer
Available date2024-03-11T06:03:07Z
Publication Date2023
Publication NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ResourceScopus
ISSN0736587X
URIhttp://hdl.handle.net/10576/52848
URIhttp://dx.doi.org/10.18653/v1/2023.acl-long.901
AbstractExtracting geolocation information from social media data enables effective disaster management, as it helps response authorities; for example, in locating incidents for planning rescue activities, and affected people for evacuation. Nevertheless, geolocation extraction is greatly understudied for the low resource languages such as Arabic. To fill this gap, we introduce IDRISI-RA, the first publicly-available Arabic Location Mention Recognition (LMR) dataset that provides human- and automatically-labeled versions in order of thousands and millions of tweets, respectively. It contains both location mentions and their types (e.g., district, city). Our extensive analysis shows the decent geographical, domain, location granularity, temporal, and dialectical coverage of IDRISI-RA. Furthermore, we establish baselines using the standard Arabic NER models and build two simple, yet effective, LMR models. Our rigorous experiments confirm the need for developing specific models for Arabic LMR in the disaster domain. Moreover, experiments show the promising domain and geographical generalizability of IDRISI-RA under zero-shot learning.
SponsorThis work was made possible by the Graduate Sponsorship Research Award (GSRA) #GSRA5-1-0527-18082 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors. We would like to thank the in-house annotators for their valuable help including Noura Abdullah, Aisha Suwaileh, Rasha Hamdoon, Na-jlaa Alfuhaida, Hana Shamayleh, Lamiaa Basyoni, Sara Alrasbi, and Nada Abo Eita.
Languageen
PublisherAssociation for Computational Linguistics (ACL)
SubjectComputational linguistics
Disaster prevention
Disasters
Zero-shot learning
Disaster management
Effective location
Experiment confirm
Geolocations
Low resource languages
Recognition models
Rescue activities
Simple++
Social media datum
Standard arabics
Location
TitleIDRISI-RA: The First Arabic Location Mention Recognition Dataset of Disaster Tweets
TypeConference Paper
Pagination16298-16317
Volume Number1
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record