SyMGiza++: A Tool for Parallel Computation of Symmetrized Word Alignment Models

Marcin Junczys-Dowmunt, Arkadiusz Szał

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

Abstract

SyMGiza++ -- a tool that computes symmetric word alignment models with the capability to take advantage of multi-processor systems -- is presented. A series of fairly simple modifications to the original IBM/Giza++ word alignm ent models allows to update the symmetrized models between each iteration of the original training algorithms. We achieve a relative alignment quality improvement of more than 17% compared to Giza++ and MGiza++ on the standard Canadian Hansards task, while maintaining the speed improvements provided by MGiza++’s capability of parallel computations.
Original languageEnglish
Title of host publicationProceedings of the International Multiconference on Computer Science and Information Technology
Place of PublicationWisła, Poland
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages397-401
Number of pages5
ISBN (Electronic)978-83-60810-27-9
Publication statusPublished - 2010

Cite this