Learning to Combine Machine Translation Systems

Evgeny Matusov, Gregor Leusch and Hermann Ney

in Learning Machine Translation

Published by The MIT Press

Published in print November 2008 | ISBN: 9780262072977
Published online August 2013 | e-ISBN: 9780262255097 | DOI:
Learning to Combine Machine Translation Systems

Show Summary Details


This chapter shows how outputs of multiple machine translation (MT) systems may be combined in order to improve translation quality. It presents a method that computes a consensus translation from the aligned MT hypotheses. The method utilizes the enhanced alignment procedure of Matusov et al. (2006), as well as its extensions. The proposed system combination approach was evaluated on well-established Chinese-to-English and Arabic-to-English large-vocabulary translation tasks. Significant improvements in translation quality were obtained when compared with the best individual MT system.

Keywords: multiple machine translation; translation quality; consensus translation

Chapter.  8596 words.  Illustrated.

Subjects: Artificial Intelligence

Full text: subscription required

How to subscribe Recommend to my Librarian

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.