Search Results for author: Petr Sojka

Found 19 papers, 7 papers with code

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

no code implementations11 May 2023 Lukáš Mikula, Michal Štefánik, Marek Petrovič, Petr Sojka

We find that while existing debiasing methods can mitigate reliance on a chosen spurious feature, the OOD performance gains of these methods can not be explained by mitigated reliance on biased features, suggesting that biases are shared among different QA datasets.

Question Answering

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

1 code implementation4 Apr 2023 Michal Štefánik, Marek Kadlčík, Piotr Gramacki, Petr Sojka

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.

In-Context Learning

Soft Alignment Objectives for Robust Adaptation of Language Generation

1 code implementation29 Nov 2022 Michal Štefánik, Marek Kadlčík, Petr Sojka

Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application.

Domain Adaptation Machine Translation +4

Interpretable Gait Recognition by Granger Causality

no code implementations14 Jun 2022 Michal Balazia, Katerina Hlavackova-Schindler, Petr Sojka, Claudia Plant

We apply the graphical Granger model (GGM) to obtain the so-called Granger causal graph among joints as a discriminative and visually interpretable representation of a person's gait.

Causal Inference Gait Recognition

Adaptor: Objective-Centric Adaptation Framework for Language Models

1 code implementation ACL 2022 Michal Štefánik, Vít Novotný, Nikola Groverová, Petr Sojka

Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks.

Unsupervised Domain Adaptation

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

no code implementations8 Oct 2021 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 learning algorithms: the Latent Dirichlet Allocation (LDA) and the Latent Semantic Indexing (LSI).

BIG-bench Machine Learning Classification +1

Regressive Ensemble for Machine Translation Quality Evaluation

1 code implementation WMT (EMNLP) 2021 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.

Machine Translation Translation

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

no code implementations1 Jun 2021 Dávid Lupták, Vít Novotný, Michal Štefánik, Petr Sojka

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 are sometimes more important than text for understanding.

Math Retrieval

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

1 code implementation19 Apr 2021 Vít Novotný, Michal Štefánik, Eniafe Festus Ayetiran, Petr Sojka, Radim Řehůřek

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 performance on the intrinsic word analogy task.

Language Modelling Machine Translation +1

EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses

no code implementations27 Feb 2021 Eniafe Festus Ayetiran, Petr Sojka, Vít Novotný

We report evaluation results on 11 benchmark datasets involving WSD and Word Similarity tasks and show that our method for enhancing distributional semantic structures improves embeddings quality on the baselines.

Semantic Similarity Semantic Textual Similarity +2

Text classification with word embedding regularization and soft similarity measure

1 code implementation10 Mar 2020 Vít Novotný, Eniafe Festus Ayetiran, Michal Štefánik, Petr Sojka

In our work, we investigate the individual and joint effect of the two word embedding regularization techniques on the document processing speed and the task performance of the SCM and the WMD on text classification.

Document Classification General Classification +4

Gait Recognition from Motion Capture Data

no code implementations24 Aug 2017 Michal Balazia, Petr Sojka

This paper contributes to the state-of-the-art with a statistical approach for extracting robust gait features directly from raw data by a modification of Linear Discriminant Analysis with Maximum Margin Criterion.

Gait Recognition General Classification

Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines

no code implementations WS 2017 Jan Rygl, Jan Pomik{\'a}lek, Radim {\v{R}}eh{\r{u}}{\v{r}}ek, Michal R{\r{u}}{\v{z}}i{\v{c}}ka, V{\'\i}t Novotn{\'y}, Petr Sojka

We empirically demonstrate its querying performance and quality by applying this solution to the task of semantic searching over a dense vector representation of the entire English Wikipedia.

Information Retrieval Representation Learning

You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data

no code implementations28 Jun 2017 Michal Balazia, Petr Sojka

This work offers a design of a video surveillance system based on a soft biometric -- gait identification from MoCap data.

Gait Identification

An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods

no code implementations4 Jan 2017 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 from motion capture (MoCap) data.

Gait Recognition

Walker-Independent Features for Gait Recognition from Motion Capture Data

no code implementations22 Sep 2016 Michal Balazia, Petr Sojka

MoCap-based human identification, as a pattern recognition discipline, can be optimized using a machine learning approach.

Gait Recognition

Learning Robust Features for Gait Recognition by Maximum Margin Criterion

no code implementations14 Sep 2016 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.

Gait Recognition

Software Framework for Topic Modelling with Large Corpora

1 code implementation Workshop On New Challenges For NLP Frameworks 2010 Radim Řehůřek, Petr Sojka

Large corpora are ubiquitous in today’s world and memory quickly becomes the limiting factor in practical applications of the Vector Space Model (VSM).

Topic Models

Cannot find the paper you are looking for? You can Submit a new open access paper.