Jindřich Libovický

+420 951 554 359
+420 257 223 293
Malostranské náměstí 25
118 00 Praha 1
Czech Republic

Main Research Interests

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


Curriculum Vitae


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


  • 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


Selected Bibliography

  • Jindřich Libovický, Jindřich Helcl. “Attention Strategies for Multi-Source Sequence-to-Sequence Learning.” In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. pp. 196-202. Association for Computational Linguistics, Vancouver, Canada. 2017. [pdf, bib, slides]
    Awarded as an outstanding paper.
  • Jindřich Helcl, Jindřich Libovický. “Neural Monkey: An Open-source Tool for Sequence Learning.” In: The Prague Bulletin of Mathematical Linguistics107. pp. 3–17. Charles University, Prague, Czech Republic, 2017. [pdf, github
  • Jindřich Libovický, Jindřich Helcl, Marek Tlustý, Pavel Pecina and Ondřej Bojar. “CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks.” In: Proceedings of the First Conference on Machine Translation (WMT). Association for Computational Linguistics, Berlin, Germany. 2016. [pdf, bib]
  • Jindřich Libovický. “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, Portorož, Slovenia. 2016. [pdf]
  • Jindřich Libovický, Lukáš Neumann, Pavel Pecina, and Jiří Matas. “A Machine Learning Approach to Hypotheses Decoding in Scene Text Recognition.” In: ACCV 2014: Computer Vision - ACCV 2014 Workshops. pp 169–180.  Springer, Cham, Switzerland. 2015. [slides]
  • Rudofl Kadlec, Miroslav Vodolan, Jindřich Libovický, Jan Macek, and Jan Kleindienst. “Knowledge-based dialog state tracking.” In Spoken Language Technology Workshop (SLT), 2014 IEEE, pp. 348–353. IEEE, 2014.
  • Jindřich Libovický, and Pavel Pecina. “Tolerant BLEU: a Submission to the WMT14 Metrics Task.“ In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 409–412. Association for Computational Linguistics, Baltimore, USA. 2014. [pdf, bibposter]
  • Rudolf Kadlec, Jindřich Libovický, Jan Macek, and Jan Kleindienst. “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, Gothenburg, Sweden. 2014. [pdf, bib]

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

Recent Blog Posts

​Visit my blog at jlibovicky.github.io.


  • 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]