Home /
Papers /
Building a Lemmatizer and a Spell-checker for Sorani Kurdish

Building a Lemmatizer and a Spell-checker for Sorani Kurdish

Authors

September 28, 2018

Part of Intelligent Spell Checking Project

Abstract

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 report a best first-ranked correction accuracy of 96.4% with a lexicon and 87% without a lexicon.

Keywords

Spell Checking Sorani Kurdish Lemmatization Edit Distance N-grams

Citation

Salavati, S., & Ahmadi, S. Building a Lemmatizer and a Spell-checker for Sorani Kurdish. Language & Technology Conference, 2017; arXiv version deposited 2018.

Publication Details

DOI 10.48550/arXiv.1809.10763

Authors 2 authors

Read Full Paper View Project Back to Papers