Attention strategies for multi-source sequence-to-sequence learning J Libovický, J Helcl arXiv preprint arXiv:1704.06567, 2017 | 205 | 2017 |
End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification J Libovický, J Helcl arXiv preprint arXiv:1811.04719, 2018 | 163 | 2018 |
Multimodal abstractive summarization for how2 videos S Palaskar, J Libovický, S Gella, F Metze arXiv preprint arXiv:1906.07901, 2019 | 118* | 2019 |
Czeng 1.6: Enlarged Czech-English parallel corpus with processing tools dockered O Bojar, O Dušek, T Kocmi, J Libovický, M Novák, M Popel, R Sudarikov, ... International Conference on Text, Speech, and Dialogue, 231-238, 2016 | 106 | 2016 |
How language-neutral is multilingual BERT? J Libovický, R Rosa, A Fraser arXiv preprint arXiv:1911.03310, 2019 | 102 | 2019 |
CUNI System for the WMT17 Multimodal Translation Task J Helcl, J Libovický Proceedings of the Second Conference on Machine Translation, Volume 2 …, 2018 | 86 | 2018 |
CUNI System for the WMT18 Multimodal Translation Task J Helcl, J Libovický, D Variš arXiv preprint arXiv:1811.04697, 2018 | 86 | 2018 |
Input combination strategies for multi-source transformer decoder J Libovický, J Helcl, D Mareček arXiv preprint arXiv:1811.04716, 2018 | 85 | 2018 |
CUNI system for WMT16 automatic post-editing and multimodal translation tasks J Libovický, J Helcl, M Tlustý, P Pecina, O Bojar arXiv preprint arXiv:1606.07481, 2016 | 78 | 2016 |
On the Language Neutrality of Pre-trained Multilingual Representations J Libovický, R Rosa, A Fraser arXiv preprint arXiv:2004.05160, 2020 | 72 | 2020 |
Neural Monkey: An open-source tool for sequence learning J Helcl, J Libovický The Prague Bulletin of Mathematical Linguistics 107 (1), 5, 2017 | 70 | 2017 |
Results of the WMT17 Neural MT Training Task O Bojar, J Helcl, T Kocmi, J Libovický, T Musil Proceedings of the Second Conference on Machine Translation, 525-533, 2017 | 29 | 2017 |
Why don't people use character-level machine translation? J Libovický, H Schmid, A Fraser arXiv preprint arXiv:2110.08191, 2021 | 25 | 2021 |
Speaking multiple languages affects the moral bias of language models K Hämmerl, B Deiseroth, P Schramowski, J Libovický, CA Rothkopf, ... arXiv preprint arXiv:2211.07733, 2022 | 23* | 2022 |
Knowledge-based dialog state tracking R Kadlec, M Vodolán, J Libovický, J Macek, J Kleindienst Spoken Language Technology Workshop (SLT), 2014 IEEE, 348-353, 2014 | 19 | 2014 |
Towards reasonably-sized character-level transformer NMT by finetuning subword systems J Libovický, A Fraser arXiv preprint arXiv:2004.14280, 2020 | 15 | 2020 |
Findings of the WMT 2021 shared tasks in unsupervised MT and very low resource supervised MT J Libovický, A Fraser Proceedings of the Sixth Conference on Machine Translation, 726-732, 2021 | 13 | 2021 |
Improving both domain robustness and domain adaptability in machine translation W Lai, J Libovický, A Fraser arXiv preprint arXiv:2112.08288, 2021 | 12 | 2021 |
Neural monkey: The current state and beyond J Helcl, J Libovický, T Kocmi, T Musil, O Cífka, D Variš, O Bojar 13th Conference of the Association for Machine Translation in the Americas …, 2018 | 12 | 2018 |
Probing the role of positional information in vision-language models PJ Rösch, J Libovický arXiv preprint arXiv:2305.10046, 2023 | 10 | 2023 |