Jindřich Libovický

Main Research Interests

deep learning in NLP, combining language and vision, multimodal translation, scene text recognition

Projects

• Neural Monkey
• CEMI: Center for large-scale multi-modal data interpretation
• KConnect: Khresmoi Multilingual Medical Text Analysis, Search and Machine Translation Connected in a Thriving Data-Value Chain
• Using Language Knowledge in Scene Text Recognition

Curriculum Vitae

Experience

• Research Assistant @Charles University (since 2013)
• Software Enginering Intern @Google (2017)
• Analytic Linguist Intern @Google (2016)
• Research Development Support @IBM Czech Republic (2012 – 2015)

Education

• pursuing a PhD. in Computational Linguistics, Charles University, Faculty of Mathematics and Physics (since 2013)
• Masters degree in Computational Linguistics (2011 – 2013), Charles University, Faculty of Mathematics and Physics
• Bachelor degree in Media Studies (2011 – 2014), Charles University, Faculty of Social Sciences
• Bachelor degree in Computer Science (2007 – 2011), Charles University, Faculty of Mathematics and Physics

Teaching

• Compendium of Neural Machine Translation
• Introduction to Natural Language Processing (at Czech Technical University with Zdeněk Žabokrtský and others)

Selected Bibliography

1. Jindřich Helcl, Jindřich Libovický, Tom Kocmi, Tomáš Musil, Ondřej Cífka, Dušan Variš, Ondřej Bojar (2018): Neural Monkey: The Current State and Beyond. In: The 13th Conference of The Association for Machine Translation in the Americas, Vol. 1: MT Researchers’ Track, pp. 168-176, The Association for Machine Translation in the Americas, Stroudsburg, PA, USA (biblio, batt1.pdf, batt2.pdf, bibtex)
2. Jindřich Libovický, Thomas Brovelli (Meyer), Bruno Cartoni (2018): Machine Translation Evaluation beyond the Sentence Level. In: roceedings of the 21st Annual Conference of the European Association for Machine Translation (2018), pp. 179-188, European Association for Machine Translation, Allschwil, Switzerland, ISBN 978-84-09-01901-4 (biblio, bibtex)
3. Ondřej Bojar, Jindřich Helcl, Tom Kocmi, Jindřich Libovický, Tomáš Musil (2017): Results of the WMT17 Neural MT Training Task. In: Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers, pp. 525-533, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-945626-96-8 (biblio, batt1.pdf, obd, bibtex)
4. Jindřich Helcl, Jindřich Libovický (2017): CUNI System for the WMT17 Multimodal Translation Task. In: Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers, pp. 450-457, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-945626-96-8 (biblio, batt1.pdf, obd, bibtex)
5. Jindřich Helcl, Jindřich Libovický (2017): Neural Monkey: An Open-source Tool for Sequence Learning. In: The Prague Bulletin of Mathematical Linguistics, ISSN 0032-6585, 107, pp. 5-17 (biblio, batt1.pdf, obd, bibtex)
6. Jindřich Libovický, Jindřich Helcl (2017): Attention Strategies for Multi-Source Sequence-to-Sequence Learning. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 196-202, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-945626-76-0 (biblio, batt1.pdf, batt2.pdf, obd, bibtex)
7. Ondřej Bojar, Ondřej Dušek, Tom Kocmi, Jindřich Libovický, Michal Novák, Martin Popel, Roman Sudarikov, Dušan Variš (2016): CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered. In: Text, Speech, and Dialogue: 19th International Conference, TSD 2016, Lecture Notes in Computer Science, ISSN 0302-9743, 9924, pp. 231-238, Springer International Publishing, Cham / Heidelberg / New York / Dordrecht / London, ISBN 978-3-319-45509-9 (url, biblio, obd, bibtex)
8. Jindřich Libovický (2016): Neural Scoring Function for MST Parser. In: Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), pp. 694-698, European Language Resources Association, Paris, France, ISBN 978-2-9517408-9-1 (biblio, obd, bibtex)
9. Jindřich Libovický, Jindřich Helcl, Marek Tlustý, Pavel Pecina, Ondřej Bojar (2016): CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks. In: Proceedings of the First Conference on Machine Translation (WMT). Volume 2: Shared Task Papers, pp. 646-654, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-945626-10-4 (pdf, biblio, obd, bibtex)
10. Jindřich Libovický, Pavel Pecina (2016): A Dataset and Evaluation Metric for Coherent Text Recognition from Scene Images. In: Multimodal Corpora: Computer vision and language processing, pp. 33-36, European Language Resources Association, Paris, France (pdf, biblio, obd, bibtex)
11. Jindřich Libovický, Lukáš Neumann, Pavel Pecina, Jiří Matas (2015): A Machine Learning Approach to Hypothesis Decoding in Scene Text Recognition. In: Computer Vision - ACCV 2014 Workshops, Lecture Notes in Computer Science, ISSN 0302-9743, 9009, pp. 169-180, Springer International Publishing, Switzerland, ISBN 978-3-319-16630-8 (biblio, obd, bibtex)
12. Rudolf Kadlec, Jindřich Libovický, Jan Macek, Jan Kleindienst (2014): IBM’s Belief Tracker: Results On Dialog State Tracking Challenge Datasets. In: Proceedings of the Workshop on Dialogue in Motion, pp. 10-18, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-937284-81-7 (biblio, obd, bibtex)
13. Rudolf Kadlec, Miroslav Vodolán, Jindřich Libovický, Jan Macek, Jan Kleindienst (2014): Knowledge-based Dialog State Tracking. In: Proceedings of the 2014 IEEE Spoken Language Technology Workshop (SLT), pp. 348-353, IEEE, Lake Tahoe, NV, USA, ISBN 9781479971305 (biblio, obd, bibtex)
14. Jindřich Libovický, Pavel Pecina (2014): Tolerant BLEU: a Submission to the WMT14 Metrics Task. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 409-413, Association for Computational Linguistics, Baltimore, MD, USA, ISBN 978-1-941643-17-4 (biblio, batt1.pdf, obd, bibtex)

See the full list on my Google Scholar profile or our institutes's database.

Recent Blog Posts

• 05/2017: Further, faster, stronger, dear AI
• 03/2017: Computational Linguistics in the 21st century – a private manifesto of its perpetual student
• 02/2017: Spell checking of y and in Czech using deep learning
• 11/2016: What is Neural Machine Translation Capable of?

​Visit my blog at jlibovicky.github.io.

Talks

• Proč není snadné přečíst nápis z fotky a proč bychom to měli chtít (popluarization talk at Gymnázium Kladno, 23.10. 2014) [slides]
• Learning Hypotheses Decoding in an Image Text Recognition Pipeline (at Week of Doctroal Studies at ÚFAL), 19.5. 2014 [video, slides]
• Music and Computational Linguistics (at Linguistic Monday at ÚFAL), 4.11.2013 [video, slides]
• Matematická lingvistika (popularization talk at Festival Fantazie), 4.7. 2013 [slides]