Store besparelser
Hurtig levering
Gemte
Log ind
0
Kurv
Bøger
Bestsellers
Kommer snart
Nyheder
Spil og hobby
Kurv
  1. Bog
  2. Kunstig intelligens
  3. Naturligt sprog og maskinoversættelse

Joint Training for Neural Machine Translation

Af: Yong Cheng Engelsk Hardback

Joint Training for Neural Machine Translation

Af: Yong Cheng Engelsk Hardback
Tjek vores konkurrenters priser

This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data. Second, it presents a semi-supervised approach that uses an autoencoder to reconstruct monolingual corpora, so as to incorporate these corpora into neural machine translation. It then introduces a joint training algorithm for pivot-based neural machine translation, which can be used to mitigate the data scarcity problem. Lastly it describes an end-to-end bidirectional NMT model to connect the source-to-target and target-to-source translation models, allowing the interaction of parameters between these two directional models.

Vis mere
Tjek vores konkurrenters priser
Normalpris
kr 478
Fragt: 39 kr
6 - 8 hverdage
20 kr
Pakkegebyr
God 4 anmeldelser på
Tjek vores konkurrenters priser

This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data. Second, it presents a semi-supervised approach that uses an autoencoder to reconstruct monolingual corpora, so as to incorporate these corpora into neural machine translation. It then introduces a joint training algorithm for pivot-based neural machine translation, which can be used to mitigate the data scarcity problem. Lastly it describes an end-to-end bidirectional NMT model to connect the source-to-target and target-to-source translation models, allowing the interaction of parameters between these two directional models.

Vis mere
Se mere i:
Produktdetaljer
Sprog: Engelsk
Sider: 78
ISBN-13: 9789813297470
Indbinding: Hardback
Udgave:
ISBN-10: 9813297476
Kategori: Naturligt sprog og maskinoversættelse
Udg. Dato: 6 sep 2019
Længde: 0mm
Bredde: 155mm
Højde: 235mm
Forlag: Springer Verlag, Singapore
Oplagsdato: 6 sep 2019
Forfatter(e): Yong Cheng
Forfatter(e) Yong Cheng

Kategori Naturligt sprog og maskinoversættelse

ISBN-13 9789813297470

Sprog Engelsk

Indbinding Hardback

Sider 78

Udgave

Længde 0mm

Bredde 155mm

Højde 235mm

Udg. Dato 6 sep 2019

Oplagsdato 6 sep 2019

Forlag Springer Verlag, Singapore