Tom Kocmi

Malostranské náměstí 25
118 00 Praha 1
Czech Republic

Main Research Interests

Machine translation with neural networks


GAUK - Utilization of artificial neural networks in machine translation

Curriculum Vitae

2015 - now   Doctoral degree in Natural Language Processing, ÚFAL, MFF, Charles University in Prague
2013 - 2015   Mcs in Artificial Intelligence, ČVUT FEL in Prague. My master's thesis was HyperNEAT and Novelty Search for Image Recognition.
2013   Exchange study at Bishop's University in Canada, Quebec.
2010 - 2013   Bcs in Open Informatics (summa cum laude), ČVUT FEL in Prague. My bachelor's thesis was MCMC decryption.


Selected Bibliography


  • An Exploration of Word Embedding Initialization in Deep-Learning Tasks
    Tom Kocmi, Ondřej Bojar. In: ICON 2017
  • CUNI NMT System for WAT 2017 Translation Tasks
    Tom Kocmi, Dušan Variš, Ondřej Bojar. In: WAT 2017
  • Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
    Tom Kocmi, Ondřej Bojar. In: RANLP 2017
  • CUNI Submission in WMT17: Chimera Goes Neural
    Ondřej Bojar, Tom Kocmi, David Mareček, Roman Sudarikov, Dušan Variš. In: WMT 2017
  • Results of the WMT17 Neural MT Training Task
    Ondřej Bojar, Jindřich Helcl, Tom Kocmi, Jindřich Libovický, Tomáš Musil. In: WMT 2017
  • LanideNN: Multilingual Language Identification on Character Window
    Tom Kocmi, Ondřej Bojar. In: EACL 2017 Long paper