Year: 2024
Type: conference-paper
Abstract: Event-argument extraction is a challenging task, particularly in Arabic due to sparse linguistic resources.To fill this gap, we introduce the Wojood Hadath corpus (550k tokens) as an extension of Wojood, enriched with eventargument annotations.We used three types of event arguments: agent, location, and date, which we annotated as relation types.Our inter-annotator agreement evaluation resulted in 82.23% Kappa score and 87.2% F 1 -score.Additionally, we propose a novel method for event relation extraction using BERT, in which we treat the task as text entailment.This method achieves an F 1 -score of 94.01%.To further evaluate the generalization of our proposed method, we collected and annotated another out-of-domain corpus (about 80k tokens) called Wojood OutOfDomain and used it as a second test set, on which our approach achieved promising results (83.59% F 1 -score).Last but not least, we propose an end-to-end system for event-arguments extraction.This system is implemented as part of SinaTools, and both corpora are publicly available at https: //sina.birzeit.edu/wojood
Institution: Birzeit University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Birzeit University
OpenAlex ID: W4402671483