Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation

There are several approaches for improving neural machine translation for low-resource languages: monolingual data can be exploited via pretraining or data augmentation; parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; subword...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Machine translation Ročník 34; číslo 4; s. 251 - 286
Hlavní autoři:	Grönroos, Stig-Arne, Virpioja, Sami, Kurimo, Mikko
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Dordrecht Springer Netherlands 01.12.2020 Springer Nature B.V
Témata:	Artificial Intelligence Asymmetry Computational Linguistics Computer Science Czech language Danish language Denoising English language Estonian language Experiments Finnish language Languages Learning Learning transfer Machine translation Monolingualism Natural Language Processing (NLP) Noise reduction Norwegian language Parallel corpora Pretraining Regularization Sami languages Sampling Segmentation Slovak language Swedish language Translation Translation methods and strategies Vocabulary Low-resource languages Subword segmentation Multilingual machine translation Denoising sequence autoencoder Transfer learning Multi-task learning
ISSN:	0922-6567, 1573-0573
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!