| Three is better than one V Novotný, P Sojka, M Štefánik, D Lupták CEUR Workshop Proceedings, Thessaloniki, Greece, 1-30, 2020 | 30* | 2020 |
| Text classification with word embedding regularization and soft similarity measure V Novotný, EF Ayetiran, M Štefánik, P Sojka arXiv preprint arXiv:2003.05019, 2020 | 12 | 2020 |
| Ensembling ten math information retrieval systems V Novotný, M Štefánik, D Lupták, M Geletka, P Zelina, P Sojka CLEF, 2021 | 11 | 2021 |
| Combining Sparse and Dense Information Retrieval. V Novotný, M Stefánik CLEF (Working Notes), 104-118, 2022 | 10 | 2022 |
| Regressive ensemble for machine translation quality evaluation M Štefánik, V Novotný, P Sojka arXiv preprint arXiv:2109.07242, 2021 | 10 | 2021 |
| One size does not fit all: Finding the optimal subword sizes for FastText models across languages V Novotný, EF Ayetiran, D Bačovský, D Lupták, M Štefánik, P Sojka arXiv preprint arXiv:2102.02585, 2021 | 9* | 2021 |
| Applications of deep language models for reflective writings J Nehyba, M Štefánik Education and Information Technologies 28 (3), 2961-2999, 2023 | 8 | 2023 |
| When fasttext pays attention: Efficient estimation of word representations using constrained positional weighting V Novotný, M Štefánik, EF Ayetiran, P Sojka, R Řehůřek arXiv preprint arXiv:2104.09691, 2021 | 7 | 2021 |
| Quo Vadis, Math Information Retrieval. P Sojka, V Novotný, EF Ayetiran, D Lupták, M Stefánik RASLAN, 117-128, 2019 | 7 | 2019 |
| Adaptor: Objective-Centric Adaptation Framework for Language Models M Štefánik, V Novotný, N Groverová, P Sojka arXiv preprint arXiv:2203.03989, 2022 | 6 | 2022 |
| Calc-x and calcformers: Empowering arithmetical chain-of-thought through interaction with symbolic systems M Kadlčík, M Štefánik, O Sotolář, V Martinek arXiv preprint arXiv:2305.15017, 2023 | 4 | 2023 |
| Can In-context Learners Learn a Reasoning Concept from Demonstrations? M Štefánik, M Kadlčík ACL 2023 Natural Language Reasoning and Structured Explanations workshop, 2022 | 4 | 2022 |
| Methods for Estimating and improving robustness of language models M Štefánik arXiv preprint arXiv:2206.08446, 2022 | 3 | 2022 |
| Diverse Semantics Representation is King. M Geletka, V Kalivoda, M Stefánik, M Toma, P Sojka CLEF (Working Notes), 28-39, 2022 | 3 | 2022 |
| People and places of historical europe: bootstrapping annotation pipeline and a new corpus of named entities in late medieval texts V Novotný, K Luger, M Štefánik, T Vrabcová, A Horák arXiv preprint arXiv:2305.16718, 2023 | 2 | 2023 |
| Resources and Few-shot Learners for In-context Learning in Slavic Languages M Štefánik, M Kadlčík, P Gramacki, P Sojka arXiv preprint arXiv:2304.01922, 2023 | 2 | 2023 |
| Towards general document understanding through question answering Š Ščavnická, M Štefánik, M Kadlčík, M Geletka, P Sojka RASLAN 2022 Recent Advances in Slavonic Natural Language Processing, 183, 2022 | 2 | 2022 |
| Soft Alignment Objectives for Robust Adaptation of Language Generation M Štefánik, M Kadlčík, P Sojka arXiv preprint arXiv:2211.16550, 2022 | 2 | 2022 |
| Stream4Flow: Software for mining and analysis of the large volumes of network traffic T Jirsík, M Čermák, D Tovarňák, JS Paulovič, M Štefánik | 2 | 2016 |
| Concept-aware Data Construction Improves In-context Learning of Language Models M Štefánik, M Kadlčík, P Sojka arXiv preprint arXiv:2403.09703, 2024 | 1* | 2024 |
Petr SojkaAssociate Professor of Computer Science, Masaryk University在 fi.muni.cz 的电子邮件经过验证
