Differentlyfromthephrase-based paradigm,neural machine translation(NMT) operates on word and sentence representations in a continuous space.This makes the decoding process not only more difficult to interpret, but also harder to influence with external knowledge. For the latter problem, effective solutions like the XML-markup used by phrase-based models to inject fixed translation options as constraints at decoding time are not yet available. We propose a “guide”mechanism that enhances an existingNMT decoder with the ability to prioritize and adequately handle translation options presented in the form of XML annotations of source words. Positive results obtained in two different translation tasks indicate the effectiveness of our approach.

Guiding Neural Machine Translation Decoding with External Knowledge

Rajen Chatterjee;Matteo Negri;Marco Turchi;Marcello Federico;
2017

Abstract

Differentlyfromthephrase-based paradigm,neural machine translation(NMT) operates on word and sentence representations in a continuous space.This makes the decoding process not only more difficult to interpret, but also harder to influence with external knowledge. For the latter problem, effective solutions like the XML-markup used by phrase-based models to inject fixed translation options as constraints at decoding time are not yet available. We propose a “guide”mechanism that enhances an existingNMT decoder with the ability to prioritize and adequately handle translation options presented in the form of XML annotations of source words. Positive results obtained in two different translation tasks indicate the effectiveness of our approach.
978-1-945626-96-8
File in questo prodotto:
File Dimensione Formato  
document (3).pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: DRM non definito
Dimensione 262.99 kB
Formato Adobe PDF
262.99 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/313124
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact