Papers by Martin Tamajka
SlovakBERT: Slovak Masked Language Model (2022.findings-emnlp)
Copied to clipboard
Matúš Pikuliak, Štefan Grivalský, Martin Konôpka, Miroslav Blšták, Martin Tamajka, Viktor Bachratý, Marian Simko, Pavol Balážik, Michal Trnka, Filip Uhlárik
| Challenge: | SlovakBERT is a new masked language model that is based on a Web-crawled corpus. |
| Approach: | They introduce a new Slovak-only transformers-based language model called SlovkBERT . they evaluate the model on several NLP tasks and establish a benchmark for Slovakia . |
| Outcome: | The proposed model achieves state-of-the-art on several NLP tasks and achieves best results . the proposed model could be used by other Slovak researchers or NLP practitioners . |
skLEP: A Slovak General Language Understanding Benchmark (2025.findings-acl)
Copied to clipboard
Marek Suppa, Andrej Ridzik, Daniel Hládek, Tomáš Javůrek, Viktória Ondrejová, Kristína Sásiková, Martin Tamajka, Marian Simko
| Challenge: | skLEP is the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding models. |
| Approach: | They introduce a benchmark specifically designed for evaluating Slovak natural language understanding models. |
| Outcome: | The proposed benchmark covers nine tasks that span token-level, sentence-pair, document-level tasks. |
o-MEGA: Optimized Methods for Explanation Generation and Analysis (2025.emnlp-demos)
Copied to clipboard
| Challenge: | a growing number of transformer-based language models have created challenges for model transparency and trustworthiness. |
| Approach: | They propose a tool to automatically identify the most effective explainable AI methods . they evaluate o-mega on a post-claim matching pipeline using a curated dataset . |
| Outcome: | The proposed tool shows that the most effective explainable AI methods can be implemented in semantic matching tasks. |