• Čeština

Ondřej Pražák

The main area of my research is natural language processing, especially cross-lingual semantics.  This means that I am creating models that make it possible to use data in a resource-rich language (typically English) to create (or improve) models for a language for which there is not much training data (for example, Czech). I have been doing this research for four years. Besides that, I focus on machine learning methods, especially on deep neural networks.

Research and Bibliography

KONOPÍK, M., PRAŽÁK, O., SIDO, J. KnowBot: phase 1 final report. McKinsey & Company, Inc. Prague – organizační složka, 2018.
 
KONOPÍK, M., PRAŽÁK, O. LDA in Character-LSTM-CRF Named Entity Recognition. In 21st International Conference, TSD 2018, Brno, Czech Republic, September 11-14, 2018, Proceedings. Cham: Springer, 2018. s. 58-66. ISBN: 978-3-030-00793-5 , ISSN: 0302-9743
 
PRAŽÁK, O., KONOPÍK, M. Cross-Lingual SRL Based upon Universal Dependencies. In Recent Advances in Natural Language Processing Meet Deep Learning Proceedings. Shoumen: INCOMA Ltd., 2017. s. 592-690. ISBN: 978-954-452-048-9 , ISSN: 1313-8502
 
KONOPÍK, M., PRAŽÁK, O., STEINBERGER, D. Czech Dataset for Semantic Similarity and Relatedness. In Recent Advances in Natural Language Processing Meet Deep Learning. Shoumen, Bulgaria: INCOMA Ltd., 2017. s. 401-406. ISBN: 978-954-452-048-9 , ISSN: 1313-8502
 

KONOPÍK, M., PRAŽÁK, O., STEINBERGER, D., BRYCHCÍN, T. UWB at SemEval-2016 Task 2: Interpretable Semantic Textual Similarity with Distributional Semantics for Chunks. In The 10th International Workshop on Semantic Evaluation. Stroudsburg: ACL, 2016. s. 803-808. ISBN: 978-1-941643-95-2

KONOPÍK, M., PRAŽÁK, O. Information Sources of Word Semantics Methods. In Speech and Computer. Cham: Springer, 2015. s. 243-250. ISBN: 978-3-319-23131-0

 

Contact

E-mail:  ondfa@ntis.zcu.cz

Tel.: +420 377 63 2151