I exploit statistics and machine learning to deal with:
A collection of harmonised lexical networks capturing word-formation in a cross-linguistically consistent annotation scheme for many languages.
A collection of harmonised lexical networks capturing morphological segmentation in a cross-linguistically consistent annotation scheme for many languages.
A lexical derivational network for Czech. I enlarge relations captured, prepare manual annotations, and label semantics.
A lexical derivational network for Russian. It adheres the same principles as DeriNet and is included in Universal Derivations.
A collection of models of word embeddings for Czech, trained on a large Czech corpus data.