43 citations · 141 across the 21 of their papers we have counts for
21 papers
The Art of Hierarchical Competing Patterns: Gaussian Process Optimization of Hyphenation
Ondřej Sojka, Petr Sojka
Hyphenation patterns remain a compact and widely deployed solution for word breaking in typesetting systems, text processors, and web rendering engines, but their generation still…
Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models
Lukáš Mikula, Michal Štefánik, Marek Petrovič +1
While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious corre…
Resources and Few-shot Learners for In-context Learning in Slavic Languages
Michal Štefánik, Marek Kadlčík, Piotr Gramacki +1
Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the abi…
Soft Alignment Objectives for Robust Adaptation of Language Generation
Michal Štefánik, Marek Kadlčík, Petr Sojka
Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further traini…
Adaptor: Objective-Centric Adaptation Framework for Language Models
Michal Štefánik, Vít Novotný, Nikola Groverová +1
Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces Adaptor library that transpose…
Towards Math-Aware Automated Classification and Similarity Search of Scientific Publications: Methods of Mathematical Content Representations
Michal Růžička, Petr Sojka
In this paper, we investigate mathematical content representations suitable for the automated classification of and the similarity search in STEM documents using standard machine l…
Regressive Ensemble for Machine Translation Quality Evaluation
Michal Štefánik, Vít Novotný, Petr Sojka
This work introduces a simple regressive ensemble for evaluating machine translation quality based on a set of novel and established metrics. We evaluate the ensemble using a corre…
WebMIaS on Docker: Deploying Math-Aware Search in a Single Line of Code
Dávid Lupták, Vít Novotný, Michal Štefánik +1
Math informational retrieval (MIR) search engines are absent in the wide-spread production use, even though documents in the STEM fields contain many mathematical formulae, which a…
When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
Vít Novotný, Michal Štefánik, Eniafe Festus Ayetiran +2
In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art…
EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
Eniafe Festus Ayetiran, Petr Sojka, Vít Novotný
Several language applications often require word semantics as a core part of their processing pipeline, either as precise meaning inference or semantic similarity. Multi-sense embe…
One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages
Vít Novotný, Eniafe Festus Ayetiran, Dalibor Bačovský +3
Unsupervised representation learning of words from large multilingual corpora is useful for downstream tasks such as word sense disambiguation, semantic text similarity, and inform…
Text classification with word embedding regularization and soft similarity measure
Vít Novotný, Eniafe Festus Ayetiran, Michal Štefánik +1
Since the seminal work of Mikolov et al., word embeddings have become the preferred word representations for many natural language processing tasks. Document similarity measures ex…
MIaS: Math-Aware Retrieval in Digital Mathematical Libraries
Petr Sojka, Michal Růžička, Vít Novotný
Digital mathematical libraries (DMLs) such as arXiv, Numdam, and EuDML contain mainly documents from STEM fields, where mathematical formulae are often more important than text for…
Gait Recognition from Motion Capture Data
Michal Balazia, Petr Sojka
Gait recognition from motion capture data, as a pattern classification discipline, can be improved by the use of machine learning. This paper contributes to the state-of-the-art wi…
Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines
Jan Rygl, Jan Pomikálek, Radim Řehůřek +3
Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to `vector similarity searching' over dense seman…
You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data
Michal Balazia, Petr Sojka
This work offers a design of a video surveillance system based on a soft biometric -- gait identification from MoCap data. The main focus is on two substantial issues of the video…
An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods
Michal Balazia, Petr Sojka
As a contribution to reproducible research, this paper presents a framework and a database to improve the development, evaluation and comparison of methods for gait recognition fro…
Walker-Independent Features for Gait Recognition from Motion Capture Data
Michal Balazia, Petr Sojka
MoCap-based human identification, as a pattern recognition discipline, can be optimized using a machine learning approach. Yet in some applications such as video surveillance new i…
Learning Robust Features for Gait Recognition by Maximum Margin Criterion
Michal Balazia, Petr Sojka
In the field of gait recognition from motion capture data, designing human-interpretable gait features is a common practice of many fellow researchers. To refrain from ad-hoc schem…
Combining Text and Formula Queries in Math Information Retrieval: Evaluation of Query Results Merging Strategies
Martin Líška, Petr Sojka, Michal Růžička
Specific to Math Information Retrieval is combining text with mathematical formulae both in documents and in queries. Rigorous evaluation of query expansion and merging strategies…
Math Indexer and Searcher Web Interface: Towards Fulfillment of Mathematicians' Information Needs
Martin Líška, Petr Sojka, Michal Růžička
We are designing and developing a web user interface for digital mathematics libraries called WebMIaS. It allows queries to be expressed by mathematicians through a faceted search…