Dušan Variš
Main Research Interests
- Neural Machine Translation
- Sequential Task Learning in Neural Networks
- Modularity in Neural Networks
- Japanese-English Translation
Projects
Current Projects:
- ESSLLI 2026 - 37th European Summer School in Logic, Language and Information - Head of Local Organizing Committee
- BeTok - Better Tokenization for Multilingual Language Models and Machine Translation
- TokCollate - Tokenizer Comparison and Metric Visualization Framework - initial development funded by the BeTok project
- OpusPocus - Marian machine translation training pipeline for thousands of models - initial development funded by the HPLT project
- LINDAT Translation - LINDAT translation service - model training and production deployment
- Formal Linguistics Seminar - recording of lectures (archive)
Previous Projects:
- MASAPI - Multilingual Assistant for Searching, Analysing and Processing Information and decision support
- HPLT - High Performance Language Technologies
- Bergamot - Browser-based Multilingual Translation - multi-source machine translation
- SSHOC - Social Sciences & Humanities Open Cloud - machine translation and text processing support
- ELG - European Language Grid - dockerization of translation models
- Neural Monkey - An open-source tool for sequence learning in NLP built on TensorFlow.
- Health In My Language - machine translation of medical texts from English to Czech, German, Romanian and Polish
- MTViet - Machine Translation from Vietnamese into Czech for the Purposes of the Police of the Czech Republic
- MLFix - automatic machine translation post-editing tool based on statistical machine learning (successor of Depfix)
- Treex in Docker - dockerization of the up-to-date revision of the Treex NLP framework
Curriculum Vitae
My CV (in English) is available here.
Teaching
Selected Bibliography
- Google Scholar
- ORCID: 0000-0003-4408-2186
- Scopus ID: 56582304500
- Researcher ID: P-4531-2017
Selected Talks:
Bibliography: