NLP group

Doc.Ing. Pavel Král, Ph.D.

Team leader

pkral@kiv.zcu.cz

Pavel Kral is a lecturer/researcher at the Department of Computer Science and Engineering at the University of West Bohemia (Pilsen, Czech Republic). His teaching activities concern mainly computer security and database systems. His research is focused on natural language processing, in particular automatic dialog act recognition, syntactic parsing, document classification and machine learning methods. In November 2007, he finished his Ph.D. at the Henri Poincaré University in Nancy (France) and at the University of West Bohemia. He was a member of the Speech Group at LORIA-INRIA (public research laboratory in Nancy). His Ph.D. supervisors were Yves Laprie (LORIA), Christophe Cerisara (LORIA) and Jana Kleckova (Dept. Informatics & Computer Science).

Publications

Towards Automatic Medical Report Classification in Czech

Pavel Přibáň and Josef Baloun and Jiří Martínek and Ladislav Lenc and Pavel Král
15th International Conference on Agents and Artificial Intelligence (ICAART 2023) (2023)
PDF
Language Modeling | Document Classification | Neural Networks

FCN-Boosted Historical Map Segmentation with Little Training Data

Josef Baloun and Ladislav Lenc and Pavel Král
ICDAR (2023)
PDF
Neural Networks | Image Processing

Linear Transformations for Cross-lingual Sentiment Analysis

Pavel Přibáň and Jakub Šmíd and Pavel Král
TSD (2022)
PDF
Sentiment Analysis | Neural Networks

How to Segment Handwritten Historical Chronicles Using Fully Convolutional Networks?

Josef Baloun and Pavel Král and Ladislav Lenc
Agents and Artificial Intelligence, Revised Selected Papers, 13th International Conference, ICAART 2021 (2022)
PDF
Neural Networks | Image Processing

Text Line Segmentation in Historical Newspapers

Ladislav Lenc and Jiří Martínek and Pavel Král
21th International Conference on Artificial Intelligence and Soft Computing (ICAISC 2022) (2022)
PDF
Neural Networks | Image Processing

Weak supervision for Question Type Detection with large language models

Jiří Martínek and Christophe Cerisara and Pavel Král and Ladislav Lenc and Josef Baloun
Interspeech (2022)
PDF
Language Modeling | Dialogue Act Recognition | Neural Networks

Well-calibrated confidence measures for multi-label text classification with a large number of labels

Lysimachos Maltoudoglou and Andreas Paisios and Ladislav Lenc and Jiří Martínek and Pavel Král and Harris Papadopoulos
Pattern Recognition (2022)
PDF
Document Classification | Neural Networks

Robust Grid Detection in Historical Map Images

Josef Baloun and Ladislav Lenc and Pavel Král
2022 IEEE International Conference on Image Processing (ICIP) (2022)
PDF
Image Processing

Historical Map Toponym Extraction for Efficient Information Retrieval

Ladislav Lenc and Jiří Martínek and Josef Baloun and Martin Prantl and Pavel Král
15th IAPR International Workshop on Document Analysis Systems (2022)
PDF
Neural Networks | Image Processing

Evaluation Datasets for Cross-lingual Semantic Textual Similarity

Tomáš Hercig and Pavel Král
Recent Advances in Natural Language Processing (2021)
PDF
Semantic Analysis | Neural Networks

Transfer learning for Czech Historical Named Entity Recognition

Helena Hubková and Pavel Král
Recent Advances in Natural Language Processing (2021)
PDF
Neural Networks | Named Entity Recognition

ICDAR 2021 Competition on Historical Map Segmentation

Josef Baloun and Ladislav Lenc and Pavel Král
ICDAR 2021 (2021)
PDF
Neural Networks | Image Processing

Border Detection for Seamless Connection of Historical Cadastral Maps

Ladislav Lenc and Martin Prantl and Jiří Martínek and Pavel Král
16th International Conference on Document Analysis and Recognition (ICDAR 2021) - Workshop on Graphics Recognition (GREC) (2021)
PDF
Neural Networks | Image Processing

Dialogue Act Recognition Using Visual Information

Jiří Martínek and Pavel Král and Ladislav Lenc
International Conference on Document Analysis and Recognition - ICDAR 2021 (2021)
PDF
Dialogue Act Recognition | Neural Networks | Image Processing

ChronSeg: Novel Dataset for Segmentation of Handwritten Historical Chronicles

Josef Baloun and Pavel Král and Ladislav Lenc
13th International Conference on Agents and Artificial Intelligence (2021)
PDF
Neural Networks | Image Processing

Cross-Lingual Approaches for Task-Specific Dialogue Act Recognition

Jiří Martínek and Christophe Cerisara and Pavel Král and Ladislav Lenc
17th International Conference on Artificial Intelligence Applications and Innovations (2021)
PDF
Dialogue Act Recognition | Neural Networks

HDPA: Historical document processing and analysis framework

Ladislav Lenc and Jiří Martínek and Pavel Král and Vincent Christlein
Evolving Systems (2020)
PDF
Neural Networks | Image Processing

Re-Ranking for Writer Identification and Writer Retrieval

Simon Jordan and Mathias Seuret and Pavel Král and Ladislav Lenc and Jiří Martínek and Barbara Wiermann and Tobias Schwinger and Andreas Maier and Vincent Christlein
14th IAPR International Workshop on Document Analysis Systems (2020)
PDF
Neural Networks | Image Processing

Improving Face Recognition Methods based on POEM Features

Ladislav Lenc and Pavel Král
12th International Conference on Agents and Artificial Intelligence (2020)
PDF
Neural Networks | Image Processing

Czech Historical Named Entity Corpus v 1.0

Helena Hubková and Pavel Král and Eva Pettersson
Proceedings of The 12th Language Resources and Evaluation Conference (2020)
PDF

Building an efficient OCR system for historical documents with little training data

Jiří Martínek and Ladislav Lenc and Pavel Král
Neural Computing and Applications (2020)
PDF
Neural Networks | Image Processing

Deep Generalized Max Pooling

Vincent Christlein and Anguelos Nicolaou and Pavel Král
15th International Conference on Document Analysis and Recognition (ICDAR 2019) (2019)
PDF
Neural Networks

Multi-Lingual Dialogue Act Recognition with Deep Learning Methods

Jiří Martínek and Pavel Král and Ladislav Lenc and Christophe Cerisara
Interspeech 2019 (2019)
PDF
Dialogue Act Recognition | Neural Networks

Tools for Semi-automatic Preparation of Training Data for OCR

Ladislav Lenc and Jiří Martínek and Pavel Král
Artificial Intelligence Applications and Innovations (2019)
PDF
Neural Networks

Training Strategies for OCR Systems for Historical Documents

Jiří Martínek and Ladislav Lenc and Pavel Král
Artificial Intelligence Applications and Innovations (2019)
PDF
Dialogue Act Recognition

Hybrid Training Data for Historical Text OCR

Jiří Martínek and Ladislav Lenc and Pavel Král and Anguelos Nicolaou and Vincent Christlein
15th International Conference on Document Analysis and Recognition (ICDAR 2019) (2019)
PDF
Neural Networks

Czech Text Document Corpus v 2.0

Pavel Král and Ladislav Lenc
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)
PDF
Document Classification

Neural networks for multi-lingual multi-label document classification

Jiří Martínek and Ladislav Lenc and Pavel Král
27th International Conference on Artificial Neural Networks (ICANN 2018) (2018)
PDF
Document Classification | Neural Networks

Stance and Sentiment in Czech

Tomáš Hercig and Peter Krejzl and Pavel Král
Computación y Sistemas (2018)
PDF
Sentiment Analysis

Data Harvesting and Event Detection from Czech Twitter

Václav Rajtmajer and Pavel Král
Agents and Artificial Intelligence (2018)
PDF
Semantic Analysis

Deep Neural Networks for Czech Multi-label Document Classification

Ladislav Lenc and Pavel Král
Computational Linguistics and Intelligent Text Processing (2018)
PDF
Document Classification | Neural Networks

On the effects of using word2vec representations in neural networks for dialogue act recognition

Christophe Cerisara and Pavel Král and Ladislav Lenc
Computer Speech and Language (2018)
PDF
Semantic Analysis

Semantic Space Transformations for Cross-Lingual Document Classification

Jiří Martínek and Ladislav Lenc and Pavel Král
27th International Conference on Artificial Neural Networks (ICANN 2018) (2018)
PDF
Semantic Analysis | Document Classification | Neural Networks

Word Embeddings for Multi-label Document Classification

Ladislav Lenc and Pavel Král
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017 (2017)
PDF

Real-Time Data Harvesting Method for Czech Twitter

Pavel Král and Václav Rajtmajer
in 9th International Conference on Agents and Artificial Intelligence (ICAART 2017) (2017)
PDF

Combination of Neural Networks for Multi-label Document Classification

Ladislav Lenc and Pavel Král
in 22th International Conference on Applications of Natural Language to Information Systems (NLDB 2017) (2017)
PDF
Document Classification

Unsupervised Dialogue Act Induction using Gaussian Mixtures

Tomáš Brychcín and Pavel Král
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers (2017)
PDF
Semantic Analysis | Dialogue Act Recognition

Two-Level Neural Network for Multi-label Document Classification

Ladislav Lenc and Pavel Král
in 26th International Conference on Artificial Neural Networks (ICANN 2017) (2017)
PDF
Document Classification

UWB at SemEval-2016 Task 7: Novel Method for Automatic Sentiment Intensity Determination

Ladislav Lenc and Pavel Král and Václav Rajtmajer
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016) (2016)
PDF

Semantic Features for Dialogue Act Recognition

Pavel Král and Ladislav Lenc and Christophe Cerisara
3rd International Conference on Statistical Language and Speech Processing (SLSP 2015) (2015)
PDF
Semantic Analysis | Language Modeling

Named entities as new features for Czech document classification

Pavel Král
15th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2014) (2014)
PDF
Document Classification | Named Entity Recognition

Novel Unsupervised Features for Czech Multi-label Document Classification

Tomáš Brychcín and Pavel Král
13th Mexican International Conference on Artificial Intelligence (MICAI 2014) (2014)
PDF
Semantic Analysis | Document Classification