- The ssj500k Training Corpus for Slovene Language ProcessingPublication without faculty affiliation
- Cross-Lingual Semantic Role Labeling with High-Quality Translated Training CorpusPublication without faculty affiliation
- All you ever wanted to know about corpus but were afraid to ask!Publication without faculty affiliation
- Addicter: What Is Wrong with My Translations?2011 | Faculty of Mathematics and Physics
- Trivial Transfer Learning for Low-Resource Neural Machine Translation2018 | Faculty of Mathematics and Physics
- Evaluation of Word Embedding Models in Latvian NLP Tasks Based on Publicly Available CorporaPublication without faculty affiliation
- Automatic MT Error Analysis: Hjerson Helping Addicter2012 | Faculty of Mathematics and Physics
- CUNI NMT System for WAT 2018 Translation Tasks2018 | Faculty of Mathematics and Physics
- An HMM-Based PoS Tagger for Old Church SlavonicPublication without faculty affiliation
- Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation2023 | Faculty of Mathematics and Physics
- Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing AnnotationsPublication without faculty affiliation
- Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media AnalysisPublication without faculty affiliation