Fast Decoding and Optimal Decoding for Machine Translation

Ulrich Germann, Michael Jahr, Kevin Knight, Daniel Marcu, Kenji Yamada

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

Abstract

A good decoding algorithm is critical to the success of any statistical machine translation system. The decoder's job is to find the translation that is most likely according to set of previously learned parameters (and a formula for combining them). Since the space of possible translations is extremely large, typical decoding algorithms are only able to examine a portion of it, thus risking to miss good solutions. In this paper, we compare the speed and output quality of a traditional stack-based decoding algorithm with two new decoders: a fast greedy decoder and a slow but optimal decoder that treats decoding as an integer-programming optimization problem.
Original languageEnglish
Title of host publicationProceedings of the 39th Annual Meeting on Association for Computational Linguistics
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages228-235
Number of pages8
DOIs
Publication statusPublished - 2001

Publication series

NameACL '01
PublisherAssociation for Computational Linguistics

Fingerprint Dive into the research topics of 'Fast Decoding and Optimal Decoding for Machine Translation'. Together they form a unique fingerprint.

Cite this