default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMichal Stefánik
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
Journal Articles
- 2023
[j2]Jan Nehyba
, Michal Stefánik:
Applications of deep language models for reflective writings. Educ. Inf. Technol. 28(3): 2961-2999 (2023)- 2022
- [j1]Vít Novotný, Michal Stefánik, Eniafe Festus Ayetiran, Petr Sojka, Radim Rehurek:
When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting. J. Univers. Comput. Sci. 28(2): 181-201 (2022)
Conference and Workshop Papers
- 2024
- [c21]Michal Stefánik, Marek Kadlcík, Petr Sojka:
Concept-aware Data Construction Improves In-context Learning of Language Models. ACL (Findings) 2024: 12335-12352 - [c20]Lukás Mikula, Michal Stefánik, Marek Petrovic, Petr Sojka:
Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models. EACL (1) 2024: 2179-2193 - [c19]Marek Kadlcík, Michal Stefánik:
Self-training Language Models for Arithmetic Reasoning. EMNLP (Findings) 2024: 12378-12386 - 2023
- [c18]Michal Stefánik, Marek Kadlcík, Petr Sojka:
Soft Alignment Objectives for Robust Adaptation of Language Generation. ACL (1) 2023: 8837-8853 - [c17]Vit Novotny, Kristina Luger, Michal Stefánik, Tereza Vrabcová, Ales Horák:
People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts. ACL (Findings) 2023: 14104-14113 - [c16]Marek Kadlcík, Michal Stefánik, Ondrej Sotolár, Vlastimil Martinek:
Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems. EMNLP 2023: 12101-12108 - 2022
- [c15]Michal Stefánik, Vít Novotný, Nikola Groverová, Petr Sojka:
Adaptor: Objective-Centric Adaptation Framework for Language Models. ACL (demo) 2022: 261-269 - [c14]Martin Geletka, Vojtech Kalivoda, Michal Stefánik, Marek Toma, Petr Sojka:
Diverse Semantics Representation is King. CLEF (Working Notes) 2022: 28-39 - [c13]Vít Novotný, Michal Stefánik:
Combining Sparse and Dense Information Retrieval. CLEF (Working Notes) 2022: 104-118 - [c12]Michal Stefánik:
Methods for Estimating and Improving Robustness of Language Models. NAACL-HLT (Student Research Workshop) 2022: 44-51 - [c11]Martin Geletka, Mikulás Bankovic, Dávid Melus, Sárka Scavnická, Michal Stefánik, Petr Sojka:
Information Extraction from Business Documents: A Case Study. RASLAN 2022: 35-46 - [c10]Sárka Scavnická, Michal Stefánik, Marek Kadlcík, Martin Geletka, Petr Sojka:
Towards General Document Understanding through Question Answering. RASLAN 2022: 181-188 - 2021
- [c9]Vít Novotný, Michal Stefánik, Dávid Lupták, Martin Geletka, Petr Zelina, Petr Sojka:
Ensembling Math Information Retrieval Systems: MIRMU and MSM at ARQMath 2021. CLEF (Working Notes) 2021: 82-106 - [c8]Dávid Lupták, Vít Novotný, Michal Stefánik, Petr Sojka:
WebMIaS on Docker - Deploying Math-Aware Search in a Single Line of Code. CICM 2021: 159-164 - [c7]Martin Líska, Dávid Lupták, Vít Novotný, Michal Ruzicka, Boris Shminke, Petr Sojka, Michal Stefánik, Makarius Wenzel:
CICM'21 Systems Entries. CICM 2021: 245-248 - [c6]Vít Novotný, Eniafe Festus Ayetiran, Dalibor Bacovský, Dávid Lupták, Michal Stefánik, Petr Sojka:
One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages. RANLP 2021: 1068-1074 - [c5]Michal Stefánik, Petr Sojka:
Towards Domain Robustness of Neural Language Models. RASLAN 2021: 91-103 - [c4]Michal Stefánik, Vít Novotný, Petr Sojka:
Regressive Ensemble for Machine Translation Quality Evaluation. WMT@EMNLP 2021: 1041-1048 - 2020
- [c3]Vít Novotný, Petr Sojka, Michal Stefánik, Dávid Lupták:
Three is Better than One: Ensembling Math Information Retrieval Systems. CLEF (Working Notes) 2020 - [c2]Vít Novotný, Michal Stefánik, Dávid Lupták, Petr Sojka:
Towards Useful Word Embeddings. RASLAN 2020: 37-46 - 2019
- [c1]Petr Sojka, Vít Novotný, Eniafe Festus Ayetiran, Dávid Lupták, Michal Stefánik:
Quo Vadis, Math Information Retrieval. RASLAN 2019: 117-128
Informal and Other Publications
- 2024
- [i17]Michal Stefánik, Marek Kadlcík, Petr Sojka:
Concept-aware Data Construction Improves In-context Learning of Language Models. CoRR abs/2403.09703 (2024) - [i16]Marek Kadlcík, Michal Stefánik:
Self-training Language Models for Arithmetic Reasoning. CoRR abs/2407.08400 (2024) - [i15]Jakub Stetina, Martin Fajcik, Michal Stefánik, Michal Hradis:
A Comparative Study of Text Retrieval Models on DaReCzech. CoRR abs/2411.12921 (2024) - 2023
- [i14]Michal Stefánik, Marek Kadlcík, Piotr Gramacki, Petr Sojka:
Resources and Few-shot Learners for In-context Learning in Slavic Languages. CoRR abs/2304.01922 (2023) - [i13]Lukás Mikula, Michal Stefánik, Marek Petrovic, Petr Sojka:
Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models. CoRR abs/2305.06841 (2023) - [i12]Michal Stefánik, Marek Kadlcík:
Concept-aware Training Improves In-context Learning Ability of Language Models. CoRR abs/2305.13775 (2023) - [i11]Marek Kadlcík, Michal Stefánik:
Calc-X: Enriching Arithmetical Chain-of-Thoughts Datasets by Interaction with Symbolic Systems. CoRR abs/2305.15017 (2023) - [i10]Vít Novotný, Kristýna Luger, Michal Stefánik, Tereza Vrabcová, Ales Horák:
People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts. CoRR abs/2305.16718 (2023) - 2022
- [i9]Michal Stefánik, Vít Novotný, Nikola Groverová, Petr Sojka:
AdaptOr: Objective-Centric Adaptation Framework for Language Models. CoRR abs/2203.03989 (2022) - [i8]Michal Stefánik:
Methods for Estimating and Improving Robustness of Language Models. CoRR abs/2206.08446 (2022) - [i7]Michal Stefánik, Marek Kadlcík, Petr Sojka:
Soft Alignment Objectives for Robust Adaptation in Machine Translation. CoRR abs/2211.16550 (2022) - [i6]Michal Stefánik, Marek Kadlcík:
What is Not in the Context? Evaluation of Few-shot Learners with Informative Demonstrations. CoRR abs/2212.01692 (2022) - 2021
- [i5]Vít Novotný, Eniafe Festus Ayetiran, Dávid Lupták, Michal Stefánik, Petr Sojka:
One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages. CoRR abs/2102.02585 (2021) - [i4]Vít Novotný, Michal Stefánik, Eniafe Festus Ayetiran, Petr Sojka:
When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting. CoRR abs/2104.09691 (2021) - [i3]Dávid Lupták, Vít Novotný, Michal Stefánik, Petr Sojka:
WebMIaS on Docker: Deploying Math-Aware Search in a Single Line of Code. CoRR abs/2106.00411 (2021) - [i2]Michal Stefánik, Vít Novotný, Petr Sojka:
Regressive Ensemble for Machine Translation Quality Evaluation. CoRR abs/2109.07242 (2021) - 2020
- [i1]Vít Novotný, Eniafe Festus Ayetiran, Michal Stefánik, Petr Sojka:
Text classification with word embedding regularization and soft similarity measure. CoRR abs/2003.05019 (2020)
Coauthor Index
aka: Vít Novotný
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-01-21 00:08 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
