We are the natural language processing chair and research group of the computer science institute at the University of Tartu. Our work includes research projects as well as collaborations with industrial partners and the public sector. Our areas of expertise include linguistic resources, semantic networks and representations, machine translation, syntax and morphology.
- There is now a large corpus collection of raw Estonian Text with automatic sentence splitting and tagging: BigEst. The size is 110 million sentences / 1.5 billion tokens!
- We are teaching two new masters-level courses this term: Natural Language Processing (Kairit) and Language and Image Processing (Eduard and Shahab). We also continue teaching Machine Translation, Artificial Intelligence and Syntactic Theories and Models