Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT
This addresses the lack of nested NER resources for Arabic, benefiting NLP researchers and practitioners in Arabic language processing, though it is incremental as it applies existing methods to new data.
The paper introduces Wojood, a manually annotated corpus for Arabic nested Named Entity Recognition (NER) with about 550K tokens and 21 entity types, where 22.5% of entities are nested, and trains a model using AraBERT that achieves a micro F1-score of 0.884.
This paper presents Wojood, a corpus for Arabic nested Named Entity Recognition (NER). Nested entities occur when one entity mention is embedded inside another entity mention. Wojood consists of about 550K Modern Standard Arabic (MSA) and dialect tokens that are manually annotated with 21 entity types including person, organization, location, event and date. More importantly, the corpus is annotated with nested entities instead of the more common flat annotations. The data contains about 75K entities and 22.5% of which are nested. The inter-annotator evaluation of the corpus demonstrated a strong agreement with Cohen's Kappa of 0.979 and an F1-score of 0.976. To validate our data, we used the corpus to train a nested NER model based on multi-task learning and AraBERT (Arabic BERT). The model achieved an overall micro F1-score of 0.884. Our corpus, the annotation guidelines, the source code and the pre-trained model are publicly available.