Project Overview
A curated review of published Kurdish spelling-correction research and reusable external resources. The literature includes Sorani and Kurmanji word-level correction, Hunspell-based morphological resources and contextual statistical language models. Publications and resources are attributed to their original creators and are not presented as KaiLab-created systems.
Technologies & Methods
Applications
- Writing Assistance
- Educational Language Tools
- Kurdish NLP
Related Publications
Building a Lemmatizer and a Spell-checker for Sorani Kurdish
Shahin Salavati , Sina Ahmadi (2018)
A Sorani Kurdish lemmatization and word-level spelling-correction study. The Rênûs spell checker combines character n-grams, corpus frequencies, lexicon lookup and weighted edit distance. The authors …
Spell checking algorithm for agglutinative languages: Central Kurdish as an example
Roojwan Sc. Hawezi , Muhammed Y. Azeez , Ahmed A. Qadir (2019)
A Central Kurdish spelling-correction method using a compact pattern dictionary and recursive Levenshtein-distance matching. The authors report the intended correction ranked first in 79.93% of …
Hunspell for Sorani Kurdish Spell Checking and Morphological Analysis
Sina Ahmadi (2021)
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 …
A Language Model for Spell Checking of Educational Texts in Kurdish (Sorani)
Roshna Abdulrahman , Hossein Hassani (2022)
A contextual Sorani Kurdish spelling-correction study using a trigram language model with Stupid Backoff and edit-distance candidates. The authors report 88.54% overall accuracy and 43.33% F1, with …
Kurdish Kurmanji Lemmatization and Spell-checker with Spell-correction
Hanar Hoshyar Mustafa , Rebwar M. Nabi (2023)
A Kurmanji Kurdish study combining morphological lemmatization, character bigrams and Jaccard similarity for word-level spelling correction. The authors report 90.77% correction accuracy. The paper's …
Related Datasets
Kurdish Textbooks Corpus (KTC)
Published: January 1, 2019 | Size: 31 textbooks; 693,800 tokens; 110,297 types
A Sorani corpus created from Kurdish K-12 textbooks and organized by educational subject.
KurdishHunspell
Size: 33,856 Sorani; 43,945 Kurmanji; 43,328 Zazaki declared lexical entries in the cited releases
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
Size: 385 Amani rows; 1,400 NeteweNet rows
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 …
KTC-Language-Model
Size: 94,188 unigrams; 372,903 bigrams; 521,797 trigrams
The released Sorani language-model data underlying the 2022 contextual spell-checking study. The paper reports 94,188 unigram, 372,903 bigram and 521,797 trigram types. This is a language-model …
Kurdish Language Processing Toolkit (KLPT)
Size: Not applicable as an independent spelling dataset
A public Python toolkit for Sorani and Kurmanji language processing. Its spelling-suggestion component calls Hunspell, so it is an integration layer rather than an independently evaluated spelling …