Improving Arabic neural machine translation via n-best list re-ranking

Hadj Ameur, MS, Guessoum, A and Meziane, F ORCID: 2019, 'Improving Arabic neural machine translation via n-best list re-ranking' , Machine Translation .

PDF - Accepted Version
Download (1MB) | Preview


Even though the rise of the Neural Machine Translation (NMT) paradigm hasbrought a great deal of improvement to the machine translation field, the current translationresults are still not perfect. One of the main reasons for this imperfection is the decodingtask complexity. Indeed, the problem of finding the one best translation from the space of allpossible translations was and still is a challenging problem. One of the most successful ways toaddress it is via n-best list re-ranking which attempts to reorder the n-best decoder translationsaccording to some defined features. In this paper, we propose a set of new re-ranking featuresthat can be extracted directly from the parallel corpus without needing any external tools. Thefeatures set that we propose takes into account lexical, syntactic, and even semantic aspectsof the n-best list translations. We also present a method for feature weights optimization thatuses a Quantum-behaved Particle Swarm Optimization (QPSO) algorithm. Our system hasbeen evaluated on multiple English-to-Arabic and Arabic-to-English machine translation testsets, and the obtained re-ranking results yield noticeable improvements over the baseline NMTsystems.

Item Type: Article
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre
Journal or Publication Title: Machine Translation
Publisher: Springer Verlag
ISSN: 0922-6567
Related URLs:
Depositing User: Prof Farid Meziane
Date Deposited: 12 Jul 2019 08:11
Last Modified: 26 Aug 2020 02:30

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)


Downloads per month over past year