Accès ouvert
AlexU-AIC at WojoodNER shared task: Sequence Labeling vs MRC and SWA for Arabic Named Entity Recognition
Résumé
Named entity recognition (NER) is one of many challenging tasks in Arabic Natural Language Processing.It is also the base of many critical downstream tasks to help understand the source of major trends and public opinions.In this paper, we will describe our submission in the Wojood NER Shared Task of Arabic-NLP 2023.We used a simple machine reading comprehension-based technique in the Flat NER Subtask ranking eighth on the leaderboard with a 91.13%F1-score.For the Nested NER Subtask, we fine-tuned a pre-trained language model and got a 92.61% F1 score ranking third on the leaderboard.
Citer ce document
Elkordi, S., Adly, N., Torki, M.
(2023). AlexU-AIC at WojoodNER shared task: Sequence Labeling vs MRC and SWA for Arabic Named Entity Recognition.
https://doi.org/10.18653/v1/2023.arabicnlp-1.86
Accès au document
Voir sur le dépôt sourceCe document est hébergé sur son dépôt institutionnel d'origine.
Auteur(s)
Statistiques
Consultations : 1
Téléchargements : 0