Year: 2025
Type: article
Abstract: Shekar is an open-source Python toolkit for Persian natural language processing (NLP).It provides a modular, efficient, and easy-to-use framework for tasks such as text preprocessing, tokenization, stemming, lemmatization, part-of-speech (POS) tagging, named entity recognition (NER), keyword extraction, embeddings, spell checking, and visualization.Its composable pipeline design supports reproducible workflows that scale effectively from basic text processing to large-scale corpus analysis.
DOI: 10.21105/joss.09128
Author: Ahmad Amirivojdan
Institution: University of Tennessee at Knoxville
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4415399735