- Subword Pooling Makes a DifferencePublication without faculty affiliation
- On longest palindromic subwords of finite binary words2021 | Faculty of Mathematics and Physics
- Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi and Nepali2022 | Faculty of Mathematics and Physics
- Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems2020 | Faculty of Mathematics and Physics
- Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation2023 | Faculty of Mathematics and Physics
- Transfer learning and subword sampling for asymmetric-resource one-to-many neural translationPublication without faculty affiliation
- Subwords-Only Alternatives to fastText for Morphologically Rich LanguagesPublication without faculty affiliation
- On highly palindromic words2009 | Faculty of Mathematics and Physics
- Character-level NMT and language similarity2023 | Faculty of Mathematics and Physics
- Why don’t people use character-level machine translation?2022 | Faculty of Mathematics and Physics
- Morphological and Language-Agnostic Word Segmentation for NMT2018 | Faculty of Mathematics and Physics
- FJWU participation for the WMT20 Biomedical Translation TaskPublication without faculty affiliation
- IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary InitializationPublication without faculty affiliation
- The Ehrenfeucht-Silberger problem2012 | Faculty of Mathematics and Physics
- Training on Synthetic Noise Improves Robustness to Natural Noise in Machine TranslationPublication without faculty affiliation
- Cut Hierarchies for Restarting automata and Marcus t-Contextual grammars +12005 | Faculty of Mathematics and Physics
- ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution2023 | Faculty of Mathematics and Physics
- Limitations and Challenges of Unsupervised Cross-lingual Pre-trainingPublication without faculty affiliation
- On the Linguistic Representational Power of Neural Machine Translation ModelsPublication without faculty affiliation
- CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction2019 | Faculty of Mathematics and Physics
- The Role of Compounds in Human vs. Machine Translation Quality2023 | Faculty of Mathematics and Physics
- The SIGMORPHON 2022 Shared Task on Morpheme Segmentation2022 | Faculty of Mathematics and Physics
- LINSPECTOR: Multilingual Probing Tasks for Word RepresentationsPublication without faculty affiliation