Abstract
A rule-based Hunspell resource for Sorani Kurdish spelling suggestions and morphological analysis. The 2021 paper reports a 23,223-entry lexicon and 4,293 rules. Its reported evaluation should be interpreted as the performance of the evaluated 0.1.0 version, not current releases.
Keywords
Related Datasets
KurdishHunspell
A downloadable Hunspell lexical and morphological resource for Kurdish. The maintained repository includes Sorani, Kurmanji and Zazaki components. June 2025 releases declare 33,856 Sorani and 43,945 …
Central-Kurdish-Spelling-dataset
A public collection of Central Kurdish spelling-error material distributed by AsoSoft. The downloaded files contain 385 Amani rows and 1,400 NeteweNet rows, excluding headers. The maintainers document …
Citation
Ahmadi, S. (2021). Hunspell for Sorani Kurdish Spell Checking and Morphological Analysis. arXiv:2109.06374.