Named Entity Recognition for Dialectal Arabic (original) (raw)

To date, majority of research for Ara-bic Named Entity Recognition (NER) ad-dresses the task for Modern Standard Ara-bic (MSA) and mainly focuses on the newswire genre. Despite some common characteristics between MSA and Dialec-tal Arabic (DA), the significant differences between the two language varieties hinder such MSA specific systems from solving NER for Dialectal Arabic. In this paper, we present an NER system for DA specif-ically focusing on the Egyptian Dialect (EGY). Our system delivers ≈ 16 % im-provement in F1-score over state-of-the-art features. 1