State-of-the-art neural machine translation(NMT) systems are generally trained on specific domains by carefully selecting the training sets and applying proper domain adaptation techniques. In this paper we consider the real world scenario in which the target domain is not predefined, hence the system should be able to translate text from multiple domains. We compare the performance of a generic NMT system and phrase-based statistical machine translation (PBMT) system by training them on a generic parallel corpus composed of data from different domains. Our results on multi-domain English-French data showthat, in these realistic conditions, PBMT outperforms its neural counterpart. This raises the question: is NMT ready for deployment as a generic/multi-purpose MTbackbone in real-world settings?

Neural vs. Phrase-Based Machine Translation in Multi-Domain Scenario

M. Farajian;Marco Turchi;Matteo Negri;Nicola Bertoldi;Marcello Federico
2017-01-01

Abstract

State-of-the-art neural machine translation(NMT) systems are generally trained on specific domains by carefully selecting the training sets and applying proper domain adaptation techniques. In this paper we consider the real world scenario in which the target domain is not predefined, hence the system should be able to translate text from multiple domains. We compare the performance of a generic NMT system and phrase-based statistical machine translation (PBMT) system by training them on a generic parallel corpus composed of data from different domains. Our results on multi-domain English-French data showthat, in these realistic conditions, PBMT outperforms its neural counterpart. This raises the question: is NMT ready for deployment as a generic/multi-purpose MTbackbone in real-world settings?
2017
978-1-945626-35-7
File in questo prodotto:
File Dimensione Formato  
document (4).pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: DRM non definito
Dimensione 96.75 kB
Formato Adobe PDF
96.75 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/11582/313139
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact