- Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual TransferabilityPublication without faculty affiliation
- Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models2023 | Faculty of Mathematics and Physics
- Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation2019 | Faculty of Mathematics and Physics
- Team ÚFAL at CMCL 2022 Shared Task: Figuring out the correct recipe for predicting Eye-Tracking features using Pretrained Language Model2022 | Faculty of Mathematics and Physics
- Morphological annotation of the Slovak language in the Spacy library with the pretrainingPublication without faculty affiliation
- HerBERT: Efficiently pretrained transformer-based language model for PolishPublication without faculty affiliation
- Improving pretrained cross-lingual language models via self-labeled word alignmentPublication without faculty affiliation
- IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary InitializationPublication without faculty affiliation
- Emerging Cross-lingual Structure in Pretrained Language ModelsPublication without faculty affiliation
- Asking without Telling: Exploring Latent Ontologies in Contextual RepresentationsPublication without faculty affiliation
- Cross-paradigm pretraining of convolutional networks improves intracranial EEG decoding2018 | Second Faculty of Medicine
- Digital history and artificial intelligence: perspectives and risks of pretrained language modelsPublication without faculty affiliation
- Methods for Detoxification of Texts for the Russian LanguagePublication without faculty affiliation
- Parsing with Multilingual BERT, a Small Corpus, and a Small TreebankPublication without faculty affiliation
- Trankit: A light-weight transformer-based toolkit for multilingual natural language processingPublication without faculty affiliation
- Low-Resource Machine Translation Systems for Indic Languages2023 | Faculty of Mathematics and Physics
- A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank2022 | Faculty of Mathematics and Physics
- Revisiting Tri-training of Dependency ParsersPublication without faculty affiliation
- Infusing Finetuning with Semantic DependenciesPublication without faculty affiliation
- An Exploration of Word Embedding Initialization in Deep-Learning Tasks2017 | Faculty of Mathematics and Physics
- On the evolution of syntactic information encoded by BERT's contextualized representationsPublication without faculty affiliation
- Text-in-Context: Token-Level Error Detection for Table-to-Text Generation2021 | Faculty of Mathematics and Physics
- Using Language Models to Improve Rule-based Linguistic Annotation of Modern Historical Japanese CorporaPublication without faculty affiliation
- Data-to-Text Generation with Iterative Text Editing2020 | Faculty of Mathematics and Physics
- CNN for Modeling Sanskrit Originated Bengali and Hindi LanguagePublication without faculty affiliation
- Nonconvulsive Kainic Acid-Induced Seizures Elicit Age-Dependent Impairment of Memory for the Elevated Plus-Maze2000 | Second Faculty of Medicine
- Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTPublication without faculty affiliation
- CUNI Submission to MT4All Shared Task2022 | Faculty of Mathematics and Physics
- How Many Pages? Paper Length Prediction from the Metadata2020 | Faculty of Mathematics and Physics
- Specializing Multilingual Language Models: An Empirical StudyPublication without faculty affiliation