Improving Mid-Range Re-Ordering Using Templates of Factors

Hieu Hoang, Philipp Koehn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We extend the factored translation model (Koehn and Hoang, 2007) to allow translations of longer phrases composed of factors such as POS and morphological tags to act as templates for the selection and reordering of surface phrase translation. We also reintroduce the use of alignment information within the decoder, which forms an integral part of decoding in the Alignment Template System (Och, 2002), into phrase-based decoding. Results show an increase in translation performance of up to 1.0% BLEU for out-of-domain French–English translation. We also show how this method compares and relates to lexicalized reordering.
Original languageEnglish
Title of host publicationProceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009)
Place of PublicationAthens, Greece
PublisherAssociation for Computational Linguistics
Pages372-379
Number of pages8
Publication statusPublished - 1 Mar 2009

Fingerprint

Dive into the research topics of 'Improving Mid-Range Re-Ordering Using Templates of Factors'. Together they form a unique fingerprint.

Cite this