Petr Sojka

Orcid: 0000-0002-5768-4007

According to our database1, Petr Sojka authored at least 67 papers between 2000 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Concept-aware Data Construction Improves In-context Learning of Language Models.
CoRR, 2024

Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models.
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024

2023
Resources and Few-shot Learners for In-context Learning in Slavic Languages.
CoRR, 2023

Soft Alignment Objectives for Robust Adaptation of Language Generation.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2022
When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting.
J. Univers. Comput. Sci., 2022

Soft Alignment Objectives for Robust Adaptation in Machine Translation.
CoRR, 2022

Towards General Document Understanding through Question Answering.
Proceedings of the 16th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2022

Information Extraction from Business Documents: A Case Study.
Proceedings of the 16th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2022

Interpretable Gait Recognition by Granger Causality.
Proceedings of the 26th International Conference on Pattern Recognition, 2022

Diverse Semantics Representation is King.
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.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022

2021
EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses.
Knowl. Based Syst., 2021

Towards Math-Aware Automated Classification and Similarity Search of Scientific Publications: Methods of Mathematical Content Representations.
CoRR, 2021

When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting.
CoRR, 2021

One Size Does Not Fit All: Finding the Optimal N-gram Sizes for FastText Models across Languages.
CoRR, 2021

Regressive Ensemble for Machine Translation Quality Evaluation.
Proceedings of the Sixth Conference on Machine Translation, 2021

Towards Domain Robustness of Neural Language Models.
Proceedings of the 15th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2021

Application of Super-Resolution Models in Optical Character Recognition of Czech Medieval Texts.
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.
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.
Proceedings of the Intelligent Computer Mathematics - 14th International Conference, 2021

CICM'21 Systems Entries.
Proceedings of the Intelligent Computer Mathematics - 14th International Conference, 2021

Ensembling Math Information Retrieval Systems: MIRMU and MSM at ARQMath 2021.
Proceedings of the Working Notes of CLEF 2021 - Conference and Labs of the Evaluation Forum, Bucharest, Romania, September 21st - to, 2021

2020
Examination of electrodermal and cardio-vascular reactivity in virtual reality through a combined stress induction protocol.
J. Ambient Intell. Humaniz. Comput., 2020

Social Environment Simulation in VR Elicits a Distinct Reaction in Subjects with Different Levels of Anxiety and Somatoform Dissociation.
Int. J. Hum. Comput. Interact., 2020

Text classification with word embedding regularization and soft similarity measure.
CoRR, 2020

Towards Useful Word Embeddings.
Proceedings of the 14th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2020

Three is Better than One: Ensembling Math Information Retrieval Systems.
Proceedings of the Working Notes of CLEF 2020, 2020

2019
Towards Universal Hyphenation Patterns.
Proceedings of the 13th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2019

Quo Vadis, Math Information Retrieval.
Proceedings of the 13th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2019

2018
Gait Recognition from Motion Capture Data.
ACM Trans. Multim. Comput. Commun. Appl., 2018

Weighting of Passages in Question Answering.
Proceedings of the 12th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2018

MIaS: Math-Aware Retrieval in Digital Mathematical Libraries.
Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018

2017
Flexible Similarity Search of Semantic Vectors Using Fulltext Search Engines.
Proceedings of the Joint Proceedings of the International Workshops on Hybrid Statistical Semantic Understanding and Emerging Semantics, 2017

Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines.
Proceedings of the 2nd Workshop on Representation Learning for NLP, 2017

Semantic Similarities between Locations based on Ontology.
Proceedings of the 11th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2017

You are how you walk: Uncooperative MoCap gait identification for video surveillance with incomplete and noisy data.
Proceedings of the 2017 IEEE International Joint Conference on Biometrics, 2017

2016
Walker-Independent Features for Gait Recognition from Motion Capture Data.
Proceedings of the Structural, Syntactic, and Statistical Pattern Recognition, 2016

ScaleText: The Design of a Scalable, Adaptable and User-Friendly Document System for Similarity Searches.
Proceedings of the 10th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2016

Math Indexer and Searcher under the Hood: Fine-tuning Query Expansion and Unification Strategies.
Proceedings of the 12th NTCIR Conference on Evaluation of Information Access Technologies, 2016

Learning robust features for gait recognition by Maximum Margin Criterion.
Proceedings of the 23rd International Conference on Pattern Recognition, 2016

An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods.
Proceedings of the Reproducible Research in Pattern Recognition, 2016

2015
Combining Text and Formula Queries in Math Information Retrieval: Evaluation of Query Results Merging Strategies.
Proceedings of the First International Workshop on Novel Web Search Interfaces and Systems, 2015

2014
An Architecture for Scientific Document Retrieval: Using Textual and Math Entailment Modules.
Proceedings of the 8th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2014

Math Indexer and Searcher under the Hood: History and Development of a Winning Strategy.
Proceedings of the 11th NTCIR Conference on Evaluation of Information Access Technologies, 2014

Math Indexer and Searcher Web Interface - Towards Fulfillment of Mathematicians' Information Needs.
Proceedings of the Intelligent Computer Mathematics - International Conference, 2014

2013
Towards the Realistic Natural Language Representations.
Proceedings of the 7th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2013

Similarity Search for Mathematics: Masaryk University Team at the NTCIR-10 Math Task.
Proceedings of the 10th NTCIR Conference on Evaluation of Information Access Technologies, 2013

Towards Machine-Actionable Modules of a Digital Mathematics Library - The Example of DML-CZ.
Proceedings of the Intelligent Computer Mathematics, 2013

2012
Segmentation from 97% to 100%: Is It Time for Some Linguistics?
Proceedings of the 6th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2012

Exploiting semantic annotations in math information retrieval.
Proceedings of the Fifth workshop on Exploiting Semantic Annotations in Information Retrieval, 2012

2011
Building Corpora of Technical Texts: Approaches and Tools.
Proceedings of the 5th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2011

Indexing and Searching Mathematics in Digital Libraries - Architecture, Design and Scalability Issues.
Proceedings of the Intelligent Computer Mathematics - 18th Symposium, 2011

Project EuDML - A First Year Demonstration.
Proceedings of the Intelligent Computer Mathematics - 18th Symposium, 2011

The art of mathematics retrieval.
Proceedings of the 2011 ACM Symposium on Document Engineering, 2011

2010
Foreword to the Special Issue on Authoring, Digitalization and Management of Mathematical Knowledge.
Math. Comput. Sci., 2010

Effective Creation of Self-Referencing Citation Records.
Proceedings of the 4th Workshop on Recent Advances in Slavonic Natural Languages Processing, 2010

Document engineering for a digital library: PDF recompression using JBIG2 and other optimizations of PDF documents.
Proceedings of the 2010 ACM Symposium on Document Engineering, 2010

2009
Languages of Mathematics.
Proceedings of the 3rd Workshop on Recent Advances in Slavonic Natural Languages Processing, 2009

Digitization Workflow in the Czech Digital Mathematics Library.
Proceedings of the Computer Mathematics, 2009

2008
Towards Natural Natural Language Processing.
Proceedings of the 2nd Workshop on Recent Advances in Slavonic Natural Languages Processing, 2008

Automated Classification and Categorization of Mathematical Knowledge.
Proceedings of the Intelligent Computer Mathematics, 9th International Conference, 2008

2007
Classification of Multilingual Mathematical Papers in DML-CZ.
Proceedings of the 1st Workshop on Recent Advances in Slavonic Natural Languages Processing, 2007

2004
Animations in pdfTEX-Generated PDF.
Proceedings of the TeX, 2004

2003
Interactive teaching materials in PDF using JavaScript.
Proceedings of the 8th Annual SIGCSE Conference on Innovation and Technology in Computer Science Education, 2003

Rapid evaluation using multiple choice tests and TeX.
Proceedings of the 8th Annual SIGCSE Conference on Innovation and Technology in Computer Science Education, 2003

Animations in <i>PDF</i>.
Proceedings of the 8th Annual SIGCSE Conference on Innovation and Technology in Computer Science Education, 2003

2000
Competing Patterns for Language Engineering.
Proceedings of the Text, Speech and Dialogue - Third International Workshop, 2000


  Loading...