Logo UK Logo MFF

Institute of Formal and Applied Linguistics


Charles University, Czech Republic
Faculty of Mathematics and Physics

ÚFAL
Ivana Kvapilíková

Ivana Kvapilíková Ivana Muzikářová

Main Research Interests

  • Neural machine translation, unsupervised machine translation
  • Multilingual representation learning
  • Speech development in bilingual babies

Projects

The effect of bilingualism on speech perception and production in the first year of life (GACR JUNIOR STAR)
We explore the capacity of infants to discriminate between languages and examine the impact of a bilingual upbringing on this ability.
1.1.2024 - 31.12.2028  (team member)

Babel Octopus: Robust multi-source speech translation (Charles University START/SCI/089)
The project proposes methods for creating a robust simultaneous multi-source speech-to-text translation.
1.4.2021 - 31.3.2023 (team member)

Neural machine translation for low-resource languages (GAUK 1050119)
The aim of the project is to investigate methods of training machine translation models with limited access to manually translated texts. 
1.1.2019 - 31.12.2021 (principal investigator)

Neural Representations in multi-modal and multi-lingual modelling (NEUREM3) (GAČR EXPRO 19-26934X)
The NEUREM3 project encompasses basic research in speech processing (SP) and natural language processing (NLP) with accent on multi-linguality and multi-modality(speech and text processing with the support of visual information).
1.1.2019 - 31.12.2024 (team member)

 

Curriculum Vitae

Research Experience

2024 – present               Post-doc researcher

 The Czech Academy of Sciences, Institute of Psychology

 

2024 – present               Researcher

2018 – 2024                   Research assistant

Charles University in Prague, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics

 

Oct – Nov 2019               Research visit at University of the Basque Country, San Sebastián, Spain

 

Education

2018 – 2024                    Ph.D. in Computational Linguistics

Charles University in Prague, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics

Dissertation topic: Towards machine translation based on monolingual texts

 

2015 – 2019                    Bachelor's degree in Computer Science (summa cum laude)

Czech Techincal University in Prague, Faculty of Information Technology

Bachelor's thesis topic: Unsupervised machine translation between Czech and German

 

2012 – 2015                     Master's degree in Economics & Finance (summa cum laude)

2009 – 2012                     Bachelor's degree in Economics (summa cum laude)

Charles University in Prague, Faculty of Social Sciences, Institute of Economic Studies

Master's thesis topic: Measuring systemic risk in time-frequency domain

 

2015                                  Study exchange at University of Otago, Dunedin, New Zealand

2013                                  Study exchange at University of Granada, Granada, Spain

Selected Bibliography

Ivana Kvapilíková, Ondřej Bojar (2023): Boosting Unsupervised Machine Translation with Pseudo-Parallel Data. In: Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pp. 135-147, Asia-Pacific Association for Machine Translation, ISBN 978-1-952148-03-3 (url, PDF, bibtex)

Ivana Kvapilíková, Ondřej Bojar (2023): Low-Resource Machine Translation Systems for Indic Languages. In: Proceedings of the Eighth Conference on Machine Translation, pp. 954-958, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 979-8-89176-041-7 (bibtex)

Ivana Kvapilíková, Ondřej Bojar (2021): Machine Translation of Covid-19 Information Resources via Multilingual Transfer. In: ITAT 2021 2nd Workshop on Automata, Formal and Natural Languages – WAFNL 2021, pp. 176-181, Faculty of Mathematics and Physics, Praha, Czechia (pdf, local PDF, bibtex)

Ivana Kvapilíková, Mikel Artetxe, Gorka Labaka, Eneko Agirre, Ondřej Bojar (2020): Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pp. 255-262, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-952148-03-3 (url, local PDF, obd, bibtex)

Ivana Kvapilíková, Tom Kocmi, Ondřej Bojar (2020): CUNI Systems for the Unsupervised and Very Low Resource Translation Task in WMT20. In: Fifth Conference on Machine Translation - Proceedings of the Conference, pp. 1123-1128, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-948087-81-0 (local PDF, obd, bibtex)

Ivana Kvapilíková, Dominik Macháček, Ondřej Bojar (2019): CUNI Systems for the Unsupervised News Translation Task in WMT 2019. In: Fourth Conference on Machine Translation - Proceedings of the Conference, pp. 241-248, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-950737-27-7 (pdf, obd, bibtex)