Michal Stefánik

According to our database, Michal Stefánik authored at least 31 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2024

Self-training Language Models for Arithmetic Reasoning.

Marek Kadlcík, Michal Stefánik

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models.

Lukás Mikula, Michal Stefánik, Marek Petrovic, Petr Sojka

Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024

Concept-aware Data Construction Improves In-context Learning of Language Models.

Michal Stefánik, Marek Kadlcík, Petr Sojka

Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023

Applications of deep language models for reflective writings.

Jan Nehyba, Michal Stefánik

Educ. Inf. Technol., March, 2023

Calc-X: Enriching Arithmetical Chain-of-Thoughts Datasets by Interaction with Symbolic Systems.

Marek Kadlcík, Michal Stefánik

CoRR, 2023

Concept-aware Training Improves In-context Learning Ability of Language Models.

Michal Stefánik, Marek Kadlcík

CoRR, 2023

Resources and Few-shot Learners for In-context Learning in Slavic Languages.

Michal Stefánik, Marek Kadlcík, Piotr Gramacki, Petr Sojka

CoRR, 2023

Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems.

Marek Kadlcík, Michal Stefánik, Ondrej Sotolár, Vlastimil Martinek

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Soft Alignment Objectives for Robust Adaptation of Language Generation.

Michal Stefánik, Marek Kadlcík, Petr Sojka

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts.

Vit Novotny, Kristina Luger, Michal Stefánik, Tereza Vrabcová, Ales Horák

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022

When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting.

Vít Novotný, Michal Stefánik, Eniafe Festus Ayetiran, Petr Sojka, Radim Rehurek

J. Univers. Comput. Sci., 2022

What is Not in the Context? Evaluation of Few-shot Learners with Informative Demonstrations.

Michal Stefánik, Marek Kadlcík

CoRR, 2022

Soft Alignment Objectives for Robust Adaptation in Machine Translation.

Michal Stefánik, Marek Kadlcík, Petr Sojka

CoRR, 2022

Towards General Document Understanding through Question Answering.

Sárka Scavnická, Michal Stefánik, Marek Kadlcík, Martin Geletka, Petr Sojka

Proceedings of the 16th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2022

Information Extraction from Business Documents: A Case Study.

Martin Geletka, Mikulás Bankovic, Dávid Melus, Sárka Scavnická, Michal Stefánik, Petr Sojka

Proceedings of the 16th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2022

Methods for Estimating and Improving Robustness of Language Models.

Michal Stefánik

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, 2022

Combining Sparse and Dense Information Retrieval.

Vít Novotný, Michal Stefánik

Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum, Bologna, Italy, September 5th - to, 2022

Diverse Semantics Representation is King.

Martin Geletka, Vojtech Kalivoda, Michal Stefánik, Marek Toma, Petr Sojka

Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum, Bologna, Italy, September 5th - to, 2022

Adaptor: Objective-Centric Adaptation Framework for Language Models.

Michal Stefánik, Vít Novotný, Nikola Groverová, Petr Sojka

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022

2021

When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting.

Vít Novotný, Michal Stefánik, Eniafe Festus Ayetiran, Petr Sojka

CoRR, 2021

One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages.

Vít Novotný, Eniafe Festus Ayetiran, Dávid Lupták, Michal Stefánik, Petr Sojka

CoRR, 2021

Regressive Ensemble for Machine Translation Quality Evaluation.

Michal Stefánik, Vít Novotný, Petr Sojka

Proceedings of the Sixth Conference on Machine Translation, 2021

Towards Domain Robustness of Neural Language Models.

Michal Stefánik, Petr Sojka

Proceedings of the 15th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2021

One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages.

Vít Novotný, Eniafe Festus Ayetiran, Dalibor Bacovský, Dávid Lupták, Michal Stefánik, Petr Sojka

Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), 2021

WebMIaS on Docker - Deploying Math-Aware Search in a Single Line of Code.

Dávid Lupták, Vít Novotný, Michal Stefánik, Petr Sojka

Proceedings of the Intelligent Computer Mathematics - 14th International Conference, 2021

CICM'21 Systems Entries.

Martin Líska, Dávid Lupták, Vít Novotný, Michal Ruzicka, Boris Shminke, Petr Sojka, Michal Stefánik, Makarius Wenzel

Proceedings of the Intelligent Computer Mathematics - 14th International Conference, 2021

Ensembling Math Information Retrieval Systems: MIRMU and MSM at ARQMath 2021.

Vít Novotný, Michal Stefánik, Dávid Lupták, Martin Geletka, Petr Zelina, Petr Sojka

Proceedings of the Working Notes of CLEF 2021 - Conference and Labs of the Evaluation Forum, Bucharest, Romania, September 21st - to, 2021

2020

Text classification with word embedding regularization and soft similarity measure.

Vít Novotný, Eniafe Festus Ayetiran, Michal Stefánik, Petr Sojka

CoRR, 2020

Towards Useful Word Embeddings.

Vít Novotný, Michal Stefánik, Dávid Lupták, Petr Sojka

Proceedings of the 14th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2020

Three is Better than One: Ensembling Math Information Retrieval Systems.

Vít Novotný, Petr Sojka, Michal Stefánik, Dávid Lupták

Proceedings of the Working Notes of CLEF 2020, 2020

2019

Quo Vadis, Math Information Retrieval.

Petr Sojka, Vít Novotný, Eniafe Festus Ayetiran, Dávid Lupták, Michal Stefánik

Proceedings of the 13th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2019