Fast and Extensible Phrase Scoring for Statistical Machine Translation

Christian Hardmeier

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Existing tools for generating phrase tables for phrase-based Statistical Machine Translation (SMT) are generally optimised towards low memory use to allow processing of large corpora with limited memory. Whilst being a reasonable design choice, this approach does not make optimal use of resources when the sufficient memory is available. We present memscore, a new open-source tool to score phrases in memory. Besides acting as a faster drop-in replacement for existing software, it implements a number of standard smoothing techniques and provides a platform for easy experimentation with new scoring methods.
Original languageEnglish
Pages (from-to)87 - 96
Number of pages10
JournalPrague Bulletin of Mathematical Linguistics
Issue number1
Publication statusPublished - 26 Feb 2010
Event4th Machine Translation Marathon - Dublin City University, Dublin, Ireland
Duration: 25 Jan 201030 Jan 2010


Dive into the research topics of 'Fast and Extensible Phrase Scoring for Statistical Machine Translation'. Together they form a unique fingerprint.

Cite this