Projects

Ongoing Projects

• Enhancing Kurdish Natural Language Processing (KrdNLP) for Perso-Arabic Script: A Focus on Preprocessing and Tokenization (PhD Project)

  • Publication: Dasinya: A Dataset and Preprocessing Pipeline for the Badini Kurdish Dialect
    
    

• Expanding the Kurdish Part-of-Speech Annotated Corpus Using Crowdsourcing and Semi-Supervised Learning (Master Project)
  Towards Kurdish Natural Language Processing (KNLP)

• Ontology Extraction based on Kurdish Web Content
• Semantic Web Applications
• Semantic Similarity based on Document Clustering using TFIDF and K-mean
• Semantic Similarity based on Document Clustering Using Density-Based and GloVe Algorithms