The University of Southampton
University of Southampton Institutional Repository

Scalable reordering models for SMT based on multiclass SVM

Alrajeh, Abdullah and Niranjan, Mahesan (2015) Scalable reordering models for SMT based on multiclass SVM The Prague Bulletin of Mathematical Linguistics, 103, (1), pp. 65-84. (doi:10.1515/pralin-2015-0004).

Record type: Article

Abstract

In state-of-the-art phrase-based statistical machine translation systems, modelling phrase reorderings is an important need to enhance naturalness of the translated outputs, particularly when the grammatical structures of the language pairs differ significantly. Posing phrase movements as a classification problem, we exploit recent developments in solving large-scale multiclass support vector machines. Using dual coordinate descent methods for learning, we provide a mechanism to shrink the amount of training data required for each iteration. Hence, we produce significant computational saving while preserving the accuracy of the models. Our approach is a couple of times faster than maximum entropy approach and more memory-efficient (50% reduction). Experiments were carried out on an Arabic-English corpus with more than a quarter of a billion words. We achieve BLEU score improvements on top of a strong baseline system with sparse reordering features.

PDF art-alrajeh-niranjan.pdf - Other
Available under License Other.
Download (200kB)

More information

Published date: 18 April 2015
Organisations: Vision, Learning and Control

Identifiers

Local EPrints ID: 376612
URI: http://eprints.soton.ac.uk/id/eprint/376612
PURE UUID: 4a25a1f8-9155-4252-9752-66106f9b68a7

Catalogue record

Date deposited: 05 May 2015 17:25
Last modified: 17 Jul 2017 21:07

Export record

Altmetrics

Contributors

Author: Abdullah Alrajeh

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×