A POS-based preordering approach for English-to-Arabic statistical machine translation

Hadj Ameur, MS, Guessoum, A and Meziane, F ORCID: 0000-0001-9811-6914 2017, A POS-based preordering approach for English-to-Arabic statistical machine translation , in: International Conference on Arabic Language Processing (ICALP’17), 11-12 October 2017, Fez, Morocco.

[img]
Preview
PDF - Accepted Version
Download (1MB) | Preview

Abstract

In this work, we present a POS-based preordering approach that tackles both long- and short-distance reordering phenomena. Syntactic unlexicalized reordering rules are automatically extracted from a parallel corpus using only word alignment and a source-side language tagging. The reordering rules are used in a deterministic manner; this prevents the decoding speed from being bottlenecked in the reordering procedure. A new approach for both rule filtering and rule application is used to ensure a fast and efficient reordering. The tests performed on the IWSLT2016 English-to-Arabic evaluation benchmark show a noticeable increase in the overall Blue Score for our system over the baseline PSMT system.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre (SIRC)
Journal or Publication Title: Proceedings of the International Conference on Arabic Language Processing (ICALP’17)
Publisher: Springer
Related URLs:
Depositing User: Prof Farid Meziane
Date Deposited: 13 Sep 2017 10:46
Last Modified: 01 Nov 2017 22:40
URI: http://usir.salford.ac.uk/id/eprint/43747

Actions (login required)

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

Downloads

Downloads per month over past year