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

Hadj Ameur, MS, Guessoum, A and Meziane, F ORCID: https://orcid.org/0000-0001-9811-6914 2019, 'Improving Arabic neural machine translation via n-best list re-ranking' , Machine Translation, 33 , pp. 279-314.

[img]
Preview
PDF - Accepted Version
Download (1MB) | Preview
Access Information: This is a post-peer-review, pre-copyedit version of an article published in Machine Translation. The final authenticated version is available online at: http://dx.doi.org/10.1007/s10590-019-09237-6

Abstract

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

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: 20 Oct 2020 10:45
URI: http://usir.salford.ac.uk/id/eprint/51783

Actions (login required)

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

Downloads

Downloads per month over past year