Design of the Moses Decoder for Statistical Machine Translation

Hieu Hoang, Philipp Koehn

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

Abstract

We present a description of the implementation of the open source decoder for statistical machine translation which has become popular with many researchers in SMT research. The goal of the project is to create an open, high quality phrase-based decoder which can reduce the time and barrier to entry for researchers wishing to do SMT research. We discuss the major design objective for the Moses decoder, its performance relative to other SMT decoders, and the steps we are taking to ensure that its success will continue.
Original languageEnglish
Title of host publicationSoftware Engineering, Testing, and Quality Assurance for Natural Language Processing
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages58-65
Number of pages8
Publication statusPublished - 2008

Publication series

NameSETQA-NLP '08
PublisherAssociation for Computational Linguistics

Fingerprint

Dive into the research topics of 'Design of the Moses Decoder for Statistical Machine Translation'. Together they form a unique fingerprint.

Cite this