DE eng

Search in the Catalogues and Directories

Hits 1 – 4 of 4

1
Generic and Specialized Word Embeddings for Multi-Domain Machine Translation
In: International Workshop on Spoken Language Translation ; https://hal.archives-ouvertes.fr/hal-02343215 ; International Workshop on Spoken Language Translation, Nov 2019, Hong-Kong, China. ⟨10.5281/zenodo.3524978⟩ ; https://zenodo.org/communities/iwslt2019/ (2019)
BASE
Show details
2
Generic and Specialized Word Embeddings for Multi-Domain Machine Translation ...
Abstract: Supervised machine translation works well when the train and test data are sampled from the same distribution. When this is not the case, adaptation techniques help ensure that the knowledge learned from out-of-domain texts generalises to in-domain sentences. We study here a related setting, multi-domain adaptation, where the number of domains is potentially large and adapting separately to each domain would waste training resources. Our proposal transposes to neural machine translation the feature expansion technique of (Daumé III, 2007): it isolates domain-agnostic from domain-specific lexical representations, while sharing the most of the network across domains. Our experiments use two architectures and two language pairs: they show that our approach, while simple and computationally inexpensive, outperforms several strong baselines and delivers a multi-domain system that successfully translates texts from diverse sources. ...
URL: https://zenodo.org/record/3524978
https://dx.doi.org/10.5281/zenodo.3524978
BASE
Hide details
3
Generic and Specialized Word Embeddings for Multi-Domain Machine Translation ...
BASE
Show details
4
Fixing Translation Divergences in Parallel Corpora for Neural MT
In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing ; Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-01908309 ; Conference on Empirical Methods in Natural Language Processing, Nov 2018, Bruxelles, Belgium. pp.2967 - 2973 (2018)
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
4
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern