Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Ondřej Bojar"'
Autor:
Martin Popel, Marketa Tomkova, Jakub Tomek, Łukasz Kaiser, Jakob Uszkoreit, Ondřej Bojar, Zdeněk Žabokrtský
Publikováno v:
Nature Communications, Vol 11, Iss 1, Pp 1-15 (2020)
The quality of human language translation has been thought to be unattainable by computer translation systems. Here the authors present CUBBITT, a deep learning system that outperforms professional human translators in retaining text meaning in Engli
Externí odkaz:
https://doaj.org/article/a659b74d79c2411697adc8096cdc92e3
This study investigates the human translation process from English to Czech in a multi-modal scenario (images) using reaction times. We make a distinction between ambiguous and unambiguous sentences where in the former, more information would be need
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8315535cbe9424ae8f8725e6ff17f4f
https://doi.org/10.31234/osf.io/5qdgr
https://doi.org/10.31234/osf.io/5qdgr
We present Eyetracked Multi-Modal Translation (EMMT), a dataset containing monocular eye movement recordings, audio data and 4-electrode wearable electroencephalogram (EEG) data of 43 participants while engaged in sight translation task supported by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29cc08d42b7376117b2efc09fff1c597
Autor:
Arghyadeep Sen, Shantipriya Parida, Ketan Kotwal, Subhadarshi Panda, Ondřej Bojar, Satya Ranjan Dash
Publikováno v:
Intelligent Data Engineering and Analytics ISBN: 9789811666230
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09f19363ab64b6e0777db8744466c7ed
https://doi.org/10.1007/978-981-16-6624-7_7
https://doi.org/10.1007/978-981-16-6624-7_7
Publikováno v:
First Shared Task on Automatic Minuting at Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f012558bd8965bff09d101f8b14cdad0
https://doi.org/10.21437/automin.2021-1
https://doi.org/10.21437/automin.2021-1
Publikováno v:
Natural Language Engineering. 25:427-432
This paper serves as a short overview of the JNLE special issue on representation of the meaning of the sentence, bringing together traditional symbolic and modern continuous approaches. We indicate notable aspects of sentence meaning and their compa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1736ebc92b53888519f4d0b53fe13651
https://doi.org/10.1017/s1351324919000172
https://doi.org/10.1017/s1351324919000172
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::18fa9f316f6a001582d38fca2978a19b
http://arxiv.org/abs/2105.10419
http://arxiv.org/abs/2105.10419
Autor:
Łukasz Kaiser, Jakob Uszkoreit, Jakub Tomek, Ondřej Bojar, Marketa Tomkova, Zdeněk Žabokrtský, Martin Popel
Publikováno v:
Nature Communications, Vol 11, Iss 1, Pp 1-15 (2020)
Nature Communications
Nature Communications
The quality of human translation was long thought to be unattainable for computer translation systems. In this study, we present a deep-learning system, CUBBITT, which challenges this view. In a context-aware blind evaluation by human judges, CUBBITT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12dbc9c1d95bb36c0c542b8a65a6cd49
https://doi.org/10.1038/s41467-020-18073-9
https://doi.org/10.1038/s41467-020-18073-9
Autor:
Tomáš Studeník, Tomáš Musil, Daniel Hrbek, Tom Kocmi, Josef Doležal, Martina Kinská, Klára Vosecká, Rudolf Rosa, Patrícia Schmidtová, Dominik Jurko, Marie Nováková, Ondřej Dušek, David Košťák, Ondřej Bojar, David Mareček, Petr Žabka
Publikováno v:
The 2021 Conference on Artificial Life.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f05f322350bdf714b067890a3d10a31d
https://doi.org/10.1162/isal_a_00372
https://doi.org/10.1162/isal_a_00372