We present a novel online learning approach for statistical machine translation tailored to the computer assisted translation scenario. With the introduction of a simple online feature, we are able to adapt the translation model on the fly to the corrections made by the translators. Additionally, we do online adaption of the feature weights with a large margin algorithm. Our results show that our online adaptation technique outperforms the static phrase based statistical machine translation system by 6 BLEU points absolute, and a standard incremental adaptation approach by 2 BLEU points absolute.



Titolo: Online learning approaches in Computer Assisted Translation
Autori: 
Cettolo, Mauro
Federico, Marcello
mostra contributor esterni 
Data di pubblicazione: 2013
Abstract: We present a novel online learning approach for statistical machine translation tailored to the computer assisted translation scenario. With the introduction of a simple online feature, we are able to adapt the translation model on the fly to the corrections made by the translators. Additionally, we do online adaption of the feature weights with a large margin algorithm. Our results show that our online adaptation technique outperforms the static phrase based statistical machine translation system by 6 BLEU points absolute, and a standard incremental adaptation approach by 2 BLEU points absolute.
Handle: http://hdl.handle.net/11582/179814
Appare nelle tipologie:4.1 Contributo in Atti di convegno

File in questo prodotto:
FileDescrizioneTipologiaLicenza 
WMT37.pdf Post-printPUBBLICO - Pubblico con CopyrightOpen Access Visualizza/Apri
Utilizza questo identificativo per citare o creare un link a questo documento:
http://hdl.handle.net/11582/179814
  • Citazioni
  • ND

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
 
 
 
Powered by IRIS-about IRIS-Utilizzo dei cookie
Logo CINECA  Copyright © 2020