Badinan language and speech processing group (BLSP)
The Badinan Language and Speech Processing (BSLP) group is a research group at the University of Duhok in the Kurdistan Region. This group was founded to develop language resources and technologies for the Kurdish language, with a particular focus on the Badini variety of Northern Kurdish.
Most research in Kurdish Natural Language Processing (NLP) has concentrated on Central Kurdish (Sorani) and, to some extent, Northern Kurdish (Kurmanji) in its Latin script form. However, the Badini variety of Northern Kurdish has been largely overlooked. This is due to a unique combination of challenges: Badini is the only major variety of Northern Kurdish written in Arabic script, setting it apart from the Latin-based tools developed for Kurmanji. Although it shares the Arabic script with Sorani, significant linguistic differences prevent the direct use of Central Kurdish technologies for Badini.
As a result, dedicated efforts are required to build tailored language resources and tools for this dialect. This gap highlights both the urgent need and the opportunity to develop foundational language technologies for this variety.
The BSLP group is a multidisciplinary team at the University of Duhok, aiming to foster collaboration between the departments of computer science and language studies in order to provide major language resources, models and language processing tools for Badini Kurdish.