Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation

Maxim Khalilov, Jose Fonollosa, Mark Dras

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

In this paper, we start with the existing idea of taking reordering rules automatically derived from syntactic representations, and applying them in a preprocessing step before translation to make the source sentence structurally more like the target; and we propose a new approach to hierarchically extracting these rules. We evaluate this, combined with a lattice-based decoding, and show improvements over state-of-the-art distortion models.
Original languageEnglish
Title of host publicationProceedings of SSST-3
Subtitle of host publicationthird Workshop on Syntax and Structure in Statistical Translation
EditorsDekai Wu, David Chiang
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages78-86
Number of pages9
ISBN (Print)9781932432398
Publication statusPublished - 2009
EventThird Workshop on Syntax and Structure in Statistical Translation (SSST-3) - Boulder, Colorado
Duration: 5 Jun 20095 Jun 2009

Workshop

WorkshopThird Workshop on Syntax and Structure in Statistical Translation (SSST-3)
CityBoulder, Colorado
Period5/06/095/06/09

Fingerprint

Dive into the research topics of 'Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation'. Together they form a unique fingerprint.

Cite this