MS Hadj Ameur
A POS-based preordering approach for English-to-Arabic statistical machine translation
Hadj Ameur, MS; Guessoum, A; Meziane, F
Authors
A Guessoum
F Meziane
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.
Citation
Hadj Ameur, M., Guessoum, A., & Meziane, F. (2017, October). A POS-based preordering approach for English-to-Arabic statistical machine translation. Presented at International Conference on Arabic Language Processing (ICALP’17), Fez, Morocco
Presentation Conference Type | Other |
---|---|
Conference Name | International Conference on Arabic Language Processing (ICALP’17) |
Conference Location | Fez, Morocco |
Start Date | Oct 11, 2017 |
End Date | Oct 12, 2017 |
Acceptance Date | Aug 13, 2017 |
Deposit Date | Sep 13, 2017 |
Publicly Available Date | Nov 1, 2017 |
Publisher | Springer |
Publisher URL | http://www.citala.org/icalp2017/ |
Related Public URLs | http://www.springer.com/series/7899 |
Additional Information | Additional Information : Proceedings ISBN: 978-3-319-73499-6 Event Type : Conference |
Files
paper_42.pdf
(1.6 Mb)
PDF