no code implementations • EMNLP 2021 • Eva Hasler, Tobias Domhan, Jonay Trenous, Ke Tran, Bill Byrne, Felix Hieber
Building neural machine translation systems to perform well on a specific target domain is a well-studied problem.
1 code implementation • EAMT 2020 • Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit.
no code implementations • 24 Oct 2022 • Tsz Kin Lam, Eva Hasler, Felix Hieber
Customer feedback can be an important signal for improving commercial machine translation systems.
2 code implementations • 12 Jul 2022 • Felix Hieber, Michael Denkowski, Tobias Domhan, Barbara Darques Barros, Celina Dong Ye, Xing Niu, Cuong Hoang, Ke Tran, Benjamin Hsu, Maria Nadejde, Surafel Lakew, Prashant Mathur, Anna Currey, Marcello Federico
When running comparable models, Sockeye 3 is up to 126% faster than other PyTorch implementations on GPUs and up to 292% faster on CPUs.
1 code implementation • NAACL 2022 • Tobias Domhan, Eva Hasler, Ke Tran, Sony Trenous, Bill Byrne, Felix Hieber
Vocabulary selection, or lexical shortlisting, is a well-known technique to improve latency of Neural Machine Translation models by constraining the set of allowed output words during inference.
1 code implementation • AMTA 2020 • Tobias Domhan, Michael Denkowski, David Vilar, Xing Niu, Felix Hieber, Kenneth Heafield
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit.
1 code implementation • 9 Oct 2018 • Loris Bazzani, Tobias Domhan, Felix Hieber
Image captioning is an interdisciplinary research problem that stands between computer vision and natural language processing.
16 code implementations • 15 Dec 2017 • Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar, Artem Sokolov, Ann Clifton, Matt Post
Written in Python and built on MXNet, the toolkit offers scalable training and inference for the three most prominent encoder-decoder architectures: attentional recurrent neural networks, self-attentional transformers, and fully convolutional networks.
1 code implementation • EMNLP 2017 • Tobias Domhan, Felix Hieber
The performance of Neural Machine Translation (NMT) models relies heavily on the availability of sufficient amounts of parallel data, and an efficient and effective way of leveraging the vastly available amounts of monolingual data has yet to be found.