DRU at WojoodNER 2024: ICL LLM for Arabic NER

Nancy Hamdan, Hadi Hamoud, Chadi Chakra, Osama Mraikhat, Doha Albared, Fadi Zaraket


Abstract
This paper details our submission to the WojoodNER Shared Task 2024, leveraging in-context learning with large language models for Arabic Named Entity Recognition. We utilized the Command R model, to perform fine-grained NER on the Wojood-Fine corpus. Our primary approach achieved an F1 score of 0.737 and a recall of 0.756. Post-processing the generated predictions to correct format inconsistencies resulted in an increased recall of 0.759, and a similar F1 score of 0.735. A multi-level prompting method and aggregation of outputs resulted in a lower F1 score of 0.637. Our results demonstrate the potential of ICL for Arabic NER while highlighting challenges related to LLM output consistency.
Anthology ID:
2024.arabicnlp-1.106
Volume:
Proceedings of The Second Arabic Natural Language Processing Conference
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Nizar Habash, Houda Bouamor, Ramy Eskander, Nadi Tomeh, Ibrahim Abu Farha, Ahmed Abdelali, Samia Touileb, Injy Hamed, Yaser Onaizan, Bashar Alhafni, Wissam Antoun, Salam Khalifa, Hatem Haddad, Imed Zitouni, Badr AlKhamissi, Rawan Almatham, Khalil Mrini
Venues:
ArabicNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
885–893
Language:
URL:
https://aclanthology.org/2024.arabicnlp-1.106
DOI:
Bibkey:
Cite (ACL):
Nancy Hamdan, Hadi Hamoud, Chadi Chakra, Osama Mraikhat, Doha Albared, and Fadi Zaraket. 2024. DRU at WojoodNER 2024: ICL LLM for Arabic NER. In Proceedings of The Second Arabic Natural Language Processing Conference, pages 885–893, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
DRU at WojoodNER 2024: ICL LLM for Arabic NER (Hamdan et al., ArabicNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.arabicnlp-1.106.pdf