Konferenční příspěvky / Conference Papers (KIV) Collection home page

Subscribe to this collection to receive daily e-mail notification of new additions RSS Feed RSS Feed RSS Feed
Collection's Items (Sorted by Submit Date in Descending order): 21 to 40 of 180
Skala, Václav
Conditionality of Linear Systems of Equation and Matrices Using Projective Geometric Algebra

A new approach to the matrix conditionality and the solvability of the linear systems of equations is presented. It is based on the application of the geometric algebra with the projective space representation using homogeneous coordinates representation.

Skala, Václav
Geometric Transformations and Tensor Product

This contribution describes new useful geometric transformations using the tensor product. The geometric transformations are used widely in many applications, especially in CAD/CAM systems, systems for Civil Engineering, computer graphics, virtual and augmented reality, etc. The basic geometric transf...

Přibáň, Pavel , Pražák, Ondřej , Taylor, Stephen
UWB@RuShiftEval Measuring Semantic Difference as per-word Variation in Aligned Semantic Spaces

We present our system for measuring the lexical semantic change between corpora pairs, developed for the RuShiftEval competition. We measure semantic changes in a list of test words between three different corpora (for each pair), pre-Soviet, Soviet, and post-Soviet, each from a differe...

Přibáň, Pavel , Šmíd, Jakub , Mištera, Adam , Král, Pavel
Linear Transformations for Cross-lingual Sentiment Analysis

This paper deals with cross-lingual sentiment analysis in Czech, English and French languages. We perform zero-shot cross-lingual classification using five linear transformations combined with LSTM and CNN based classifiers. We compare the performance of the individual transformations, and in addition...

Bartička, Vojtěch , Pražák, Ondřej , Konopík, Miloslav , Sido, Jakub
Evaluating Attribution Methods for Explainable NLP with Transformers

This paper describes the experimental evaluation of several attribution methods on two NLP tasks: Sentiment analysis and multi-label document classification. Our motivation is to find the best method to use with Transformers to interpret model decisions. For this purpose, we introduce two&#x...

Pozzobon, Enrico , Renner, Sebastian , Mottok, Jürgen , Matoušek, Václav
An optimized Bitsliced Masked Adder for ARM Thumb-2 Controllers

The modular addition is used as a non-linear operation in ARX ciphers because it achieves the requirement of introducing non-linearity in a cryptographic primitive while only taking one clock cycle to execute on most modern archi- tectures. This makes ARX ciphers espe...

De, Sangita , Mottok, Juergen , Brada, Přemysl , Niklas, Michael
Empirical Evaluation of Semantic Alignment Quality Metrics for Vehicle Domain Component Frameworks Interface Ontologies

Semantic alignment of application software components’ ontologies represents a great interest in vehicle application domains that manipulate heterogeneous overlapping knowledge application frameworks. The most daunting impediment to their cross-enterprise collaboration is semantic interoperability. Aligning the interface...

Sido, Jakub , Ekštein, Kamil , Pražák, Ondřej , Konopík, Miloslav
On Injecting Entropy-Like Features into Deep Neural Networks for Content Relevance Assessment

This paper describes in details an innovative technique of injection of a global (or generally largescale) quality measure into a deep neural network (DNN) in order to compensate for the tendency of DNNs to found the resulting classification virtually from a superposition of local&...

Červenka, Martin , Skala, Václav
Conditionality Analysis of the Radial Basis Function Matrix

The global RBFs lead to an ill-conditioned system of linear equations, in general. This contribution analyzes conditionality of the Gauss and the Thin Plate Spline (TPS) functions. Experiments made proved dependency of the shape parameter and number of points, which can be described...

Skala, Václav , Červenka, Martin
Novel RBF Approximation Method Based on Geometrical Properties for Signal Processing

Interpolation and approximation methods are widely used in many areas. They can be divided to methods based on meshing (tessellation) of the data domain and to meshless (meshfree) methods, which do not require the domain tessellation of scattered data. Scattered n-dimensional data radia...

Pražák, Ondřej , Konopík, Miloslav , Sido, Jakub
Multilingual Coreference Resolution with Harmonized Annotations

In this paper, we present coreference resolution experiments with a newly created multi-lingual corpus CorefUD (Nedoluzhko et al.,2021). We focus on the following languages: Czech, Russian, Polish, German, Spanish, and Catalan. In addition to monolingual experiments, we combine the training data&...

Brada, Přemysl , Lipka, Richard , Holý, Lukáš , Ježek, Kamil
Interactive System Architecture Exploration:Case Studies with the IMiGEr Tool

Software systems of all kinds tend to be complex, easily comprising hundreds of components of various types and many more interconnections. Understanding of their internal structure through appropriate visualization is, therefore, a challenging task, especially when hierarchical decomposition is not&#...

Valeš, Zdeněk , Brada, Přemysl
Service API Modeling and Comparison: A Technology-Independent Approach

When service-based applications are used in systems where context varies in time or location (mobile, adaptive systems), clients may need to switch service providers for various reasons like temporary outage or geographical relocation. To prevent negative impacts on overall functionality, both&#x...

Šimečková, Lenka , Brada, Přemysl , Pícha, Petr
SPEM-Based Process Anti-Pattern Models for Detection in Project Data

A common need in software project management and process improvement is to detect the occurrence of project mishaps and management mistakes, if possible based on data available from project management and development tools. Process anti-patterns describe such re-occurring problems in textual ...

Chazalon, Joseph , Carlinet, Edwin , Chen, Yizi , Perret, Julien , Duménieu, Bertrand , Mallet, Clément , Géraud, Thierry , Nguyen, Vincent , Nguyen, Nam , Baloun, Josef , Lenc, Ladislav , Král, Pavel
ICDAR 2021 Competition on Historical Map Segmentation

This competition consists in solving several challenges which arise during the processing of images of historical maps. In the Western world, the rapid development of geodesy and cartography from the 18th century resulted in massive production of topographic maps at various scales. City...

Hubková, Helena , Král, Pavel
Transfer Learning for Czech Historical Named Entity Recognition

Nowadays, named entity recognition (NER) achieved excellent results on the standard corpora. However, big issues are emerging with a need for an application in a specific domain, because it requires a suitable annotated corpus with adapted NE tag-set. This is particularly evident in...

Hercig, Tomáš , Král, Pavel
Evaluation Datasets for Cross-lingual Semantic Textual Similarity

Semantic textual similarity (STS) systems estimate the degree of the meaning similarity between two sentences. Cross-lingual STS systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ a strongly supervised,&...

Piskorski, Jakub , Babych, Bogdan , Kancheva, Zara , Kanishcheva, Olga , Lebedeva, Maria , Marcińczuk, Michal , Nakov, Preslav , Osenova, Petya , Pivovarova, Lidia , Pollak, Senja , Přibáň, Pavel , Radev, Ivaylo , Robnik-Šikonja, Marko , Starko, Vasyl , Steinberger, Josef , Yangarber, Roman
Slav-NER: the 3rd Cross-lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic languages

This paper describes Slav-NER: the 3rd Multilingual Named Entity Challenge in Slavic languages. The tasks involve recognizing mentions of named entities in Web documents, normalization of the names, and cross-lingual linking. The Challenge covers six languages and five entity types, and is&#...

Přibáň, Pavel , Steinberger, Josef
Are the Multilingual Models Better? Improving Czech Sentiment with Transformers

In this paper, we aim at improving Czech sentiment with transformer-based models and their multilingual versions. More concretely, we study the task of polarity detection for the Czech language on three sentiment polarity datasets. We fine-tune and perform experiments with five multilingual&...

Sido, Jakub , Pražák, Ondřej , Přibáň, Pavel , Pašek, Jan , Seják, Michal , Konopík, Miloslav
Czert – Czech BERT-like Model for Language Representation

This paper describes the training process of the first Czech monolingual language representation models based on BERT and ALBERT architectures. We pre-train our models on more than 340K of sentences, which is 50 times more than multilingual models that include Czech data. We outper...

Collection's Items (Sorted by Submit Date in Descending order): 21 to 40 of 180