no code implementations • IWSLT (EMNLP) 2018 • Tom Kocmi, Dušan Variš, Ondřej Bojar
We present our submission to the IWSLT18 Low Resource task focused on the translation from Basque-to-English.
no code implementations • 7 Aug 2023 • Josef Jon, Dušan Variš, Michal Novák, João Paulo Aires, Ondřej Bojar
This paper explores negative lexical constraining in English to Czech neural machine translation.
no code implementations • WMT (EMNLP) 2021 • Josef Jon, Michal Novák, João Paulo Aires, Dušan Variš, Ondřej Bojar
This paper describes Charles University submission for Multilingual Low-Resource Translation for Indo-European Languages shared task at WMT21.
no code implementations • WMT (EMNLP) 2021 • Josef Jon, Michal Novák, João Paulo Aires, Dušan Variš, Ondřej Bojar
Our approach is based on providing the desired translations alongside the input sentence and training the model to use these provided terms.
1 code implementation • EMNLP 2021 • Dušan Variš, Ondřej Bojar
We demonstrate on a simple string editing task and a machine translation task that the Transformer model performance drops significantly when facing sequences of length diverging from the length distribution in the training data.
no code implementations • ACL 2021 • Josef Jon, João Paulo Aires, Dušan Variš, Ondřej Bojar
Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases.
no code implementations • 19 Oct 2020 • Dušan Variš, Katsuhito Sudoh, Satoshi Nakamura
We present our work in progress exploring the possibilities of a shared embedding space between textual and visual modality.
no code implementations • 19 Oct 2020 • Dušan Variš, Ondřej Bojar
In our method, we initialize the weights of the encoder and decoder with two language models that are trained with monolingual data and then fine-tune the model on parallel data using Elastic Weight Consolidation (EWC) to avoid forgetting of the original language modeling tasks.
no code implementations • 12 Nov 2018 • Jindřich Helcl, Jindřich Libovický, Dušan Variš
For our submission, we acquired both textual and multimodal additional data.