location-svg
Meine Position
Download
Joint Training for Neural Machine Translation
eBook
eBook
Fachbuch
2019

Joint Training for Neural Machine Translation

Bewertung abgeben
Autor/-in
ISBN
EAN
978-981-3297-48-7
9789813297487
Artikel-Nr.
V6EENVN
Rabatt
-21.8
%
CHF 88.50
CHF
69.25
Anzahl
1
speech-bubble-svg Beschreibung

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.

feather-svg
Stichwörter
Inhaltsverzeichnis

1. Introduction.- 2. Neural Machine Translation.- 3. Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation.- 4. Semi-supervised Learning for Neural Machine Translation.- 5. Joint Training for Pivot-based Neural Machine Translation.- 6. Joint Modeling for Bidirectional Neural Machine Translation with Contrastive Learning.- 7. Related Work.- 8. Conclusion.

feather-svg
Autor/-in
Autor/-in
Publikation
Singapur
26.08.2019
Springer Verlag
speech-bubble-svg
Sprache
Englisch
book-svg Format
eBook
PDF
78 Seiten
star-svg
Bewertungen
credit-card-svg Zahlungsarten
payment-einzahlungsschein payment-twint payment-mastercard payment-visa payment-american-express payment-post-finance payment-e-post-finance payment-apple-pay payment-google-pay samsung-pay
Bestellen Sie einfach auf Rechnung oder bezahlen Sie bequem und gebührenfrei mit Twint, Kreditkarte, PostFinance, Apple, Google oder Samsung Pay.
Rückgabe
Kein Rückgaberecht
Bei diesem eBook hat entweder der Verlag (Hersteller) das Rückgaberecht ausgeschlossen oder eine Rückgabe ist aufgrund des Vertriebssystems nicht möglich.
subcategories-svg
Passende Themen
collection-svg

# Mehr aus der Kollektion:
Springer Theses

Kollektion abonnieren
Immer die neuste Publikation erhalten
oder
eBook einzeln bestellen
  • Download
    eBook
  • Download
    eBook
  • Download
    eBook
  • Download
    eBook
  • Download
    eBook
  • Download
    eBook
  • Download
    eBook
eldar-store-white-svg
S
SPIEGEL Bestseller