Applied NLP, Computational Linguistics & Low-Resourced Languages
Specialized research and algorithmic engineering dedicated to under-resourced and non-Latinate languages. We focus our research on designing specialized tokenizers, text normalizers, morphological analyzers, and Small Language Models (SLMs).
- Gurmukhi Punjabi and related linguistic systems. Gurmukhi script computational syntax, lemmatization & phonetic parsing
- Low-resource corpus curation, synthetic data generation & SLM tuning
- Responsible AI governance, mitigation of algorithmic cultural bias