Tom Kocmi
Charles University in Prague
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Tom Kocmi.
text speech and dialogue | 2016
Ondřej Bojar; Ondřej Dušek; Tom Kocmi; Jindřich Libovický; Michal Novák; Martin Popel; Roman Sudarikov; Dusan Varis
We present a new release of the Czech-English parallel corpus CzEng. CzEng 1.6 consists of about 0.5 billion words (“gigaword”) in each language. The corpus is equipped with automatic annotation at a deep syntactic level of representation and alternatively in Universal Dependencies. Additionally, we release the complete annotation pipeline as a virtual machine in the Docker virtualization toolkit.
text speech and dialogue | 2016
Tom Kocmi; Ondřej Bojar
Skip-gram (word2vec) is a recent method for creating vector representations of words (“distributed word representations”) using a neural network. The representation gained popularity in various areas of natural language processing, because it seems to capture syntactic and semantic information about words without any explicit supervision in this respect.
Proceedings of the Second Conference on Machine Translation | 2017
Ondrej Bojar; Jindrich Helcl; Tom Kocmi; Jindrich Libovický; Tomás Musil
Archive | 2017
Tom Kocmi; Ondřej Bojar
conference of the association for machine translation in the americas | 2018
Jindrich Helcl; Jindrich Libovický; Tom Kocmi; Tomás Musil; Ondrej Cífka; Dusan Varis; Ondrej Bojar
arXiv: Computation and Language | 2018
Tom Kocmi; Ondřej Bojar
recent advances in natural language processing | 2017
Tom Kocmi; Ondrej Bojar
conference of the european chapter of the association for computational linguistics | 2017
Tom Kocmi; Ondřej Bojar
arXiv: Computation and Language | 2017
Tom Kocmi; Ondřej Bojar
Proceedings of the Second Conference on Machine Translation | 2017
Roman Sudarikov; David Marecek; Tom Kocmi; Dusan Varis; Ondrej Bojar
