
How we built a geotagged multi-dialect corpus of Albanian from Twitter, and why the machine beat native speakers
Professor of CS at UPZ & CTO of Gjirafa. NLP for low-resource languages.
Full Professor of Computer Science at the University of Prizren "Ukshin Hoti" and Co-Founder & CTO of Gjirafa. PhD from the University of Ljubljana. I work on NLP for low-resource languages, especially Albanian, LLM evaluation, hallucination detection and fake news detection. I also lead AI4ALL, an AI-literacy program in Kosovo.
Markdown supported · ⌘↵ to post
No responses yet.