Named Entity Recognition for the Kurdish Sorani Language: Dataset Creation and Comparative Analysis

This article focuses on a specific NLP task (NER) for a less-resourced language (Kurdish Sorani). The creation of a dataset is a crucial contribution, as it enables further research and development in this area. The comparative analysis suggests the evaluation of different NER models, which is valuable for identifying the best performing approaches. The focus on a specific language and task indicates a specialized research effort.

• •Focuses on Named Entity Recognition (NER) for Kurdish Sorani.
• •Involves dataset creation, a crucial step for NLP research.
• •Includes comparative analysis of different NER models.
• •Addresses a less-resourced language, contributing to linguistic diversity in AI.