Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Stojanovski, Dario"'
Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks. Self-supervised pretrained models are often fine-tuned on parallel data from one or multiple language pairs
Externí odkaz:
http://arxiv.org/abs/2209.15236
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the lexical-
Externí odkaz:
http://arxiv.org/abs/2103.10531
This paper describes the submission of LMU Munich to the WMT 2020 unsupervised shared task, in two language directions, German<->Upper Sorbian. Our core unsupervised neural machine translation (UNMT) system follows the strategy of Chronopoulou et al.
Externí odkaz:
http://arxiv.org/abs/2010.13192
Using a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data is available for one language, howe
Externí odkaz:
http://arxiv.org/abs/2009.07610
Autor:
Stojanovski, Dario, Fraser, Alexander
Achieving satisfying performance in machine translation on domains for which there is no training data is challenging. Traditional supervised domain adaptation is not suitable for addressing such zero-resource domains because it relies on in-domain p
Externí odkaz:
http://arxiv.org/abs/2004.14927
Autor:
Stojanovski, Dario
Machine translation has provided impressive translation quality for many language pairs. The improvements over the past few years are largely due to the introduction of neural networks to the field, resulting in the modern sequence-to-sequence neural
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ed9734398f84fab6765ee100e13f36d
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2015 11th International Conference on Innovations in Information Technology (IIT); 2015, p52-57, 6p
Publikováno v:
Hybrid Artificial Intelligent Systems: 10th International Conference, HAIS 2015, Bilbao, Spain, June 22-24, 2015, Proceedings; 2015, p726-737, 12p
Publikováno v:
Hybrid Artificial Intelligent Systems: 10th International Conference, HAIS 2015, Bilbao, Spain, June 22-24, 2015, Proceedings; 2015, p714-725, 12p