Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Denkowski, Michael"'
Autor:
Hieber, Felix, Denkowski, Michael, Domhan, Tobias, Barros, Barbara Darques, Ye, Celina Dong, Niu, Xing, Hoang, Cuong, Tran, Ke, Hsu, Benjamin, Nadejde, Maria, Lakew, Surafel, Mathur, Prashant, Currey, Anna, Federico, Marcello
Sockeye 3 is the latest version of the Sockeye toolkit for Neural Machine Translation (NMT). Now based on PyTorch, Sockeye 3 provides faster model implementations and more advanced features with a further streamlined codebase. This enables broader ex
Externí odkaz:
http://arxiv.org/abs/2207.05851
Autor:
Domhan, Tobias, Denkowski, Michael, Vilar, David, Niu, Xing, Hieber, Felix, Heafield, Kenneth
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, dis
Externí odkaz:
http://arxiv.org/abs/2008.04885
Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation. We propose a novel technique that com
Externí odkaz:
http://arxiv.org/abs/1805.11213
Autor:
Hieber, Felix, Domhan, Tobias, Denkowski, Michael, Vilar, David, Sokolov, Artem, Clifton, Ann, Post, Matt
We describe Sockeye (version 1.12), an open-source sequence-to-sequence toolkit for Neural Machine Translation (NMT). Sockeye is a production-ready framework for training and applying models as well as an experimental platform for researchers. Writte
Externí odkaz:
http://arxiv.org/abs/1712.05690
Autor:
Denkowski, Michael, Neubig, Graham
Interest in neural machine translation has grown rapidly as its effectiveness has been demonstrated across language and data scenarios. New research regularly introduces architectural and algorithmic improvements that lead to significant gains over "
Externí odkaz:
http://arxiv.org/abs/1706.09733
Autor:
Lavie, Alon, Denkowski, Michael J.
Publikováno v:
Machine Translation, 2009 Sep 01. 23(2/3), 105-115.
Externí odkaz:
https://www.jstor.org/stable/40783462
Publikováno v:
Proceedings of the 14th Conference of the Association for Machine Translation in the Americas: (Volume 1: Research Track), 1, 21-35
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::7d6a85b3e742df28d694d108b93aab04
https://cris.maastrichtuniversity.nl/en/publications/17ebba65-1c0a-471a-bdc4-d45d866455c9
https://cris.maastrichtuniversity.nl/en/publications/17ebba65-1c0a-471a-bdc4-d45d866455c9
Autor:
Denkowski, Michael, Lavie, Alon
As machine translation quality continues to improve, the idea of using MT to assist human translators becomes increasingly attractive. In this work, we discuss and provide empirical evidence of the challenges faced when adapting traditional MT system
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b0216a15ad149f5dab374e7f281b7c2
The pause to word ratio, the number of pauses per word in a post-edited MT segment, is an indicator of cognitive effort in post-editing (Lacruz and Shreve, 2014). We investigate how low the pause threshold can reasonably be taken, and we propose that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87bfc4fd4236819d599dffddb2be5731
Autor:
Denkowski, Michael, Lavie, Alon
This paper examines the motivation, design, and practical results of several types of human evaluation tasks for machine translation. In addition to considering annotator performance and task informativeness over multiple evaluations, we explore the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3380ebc5408c79c00ddee1a1df4bcf24