Improved Minimum Error Rate Training in Moses

Nicola Bertoldi, Barry Haddow, Jean-Baptiste Fouet

Research output: Contribution to journalArticlepeer-review

Abstract

We describe an open-source soware for minimum error rate training (MERT) for statistical machine translation (SMT). is was implemented within the Moses toolkit, although it is essentially standsalone, with the aim of replacing the existing implementation with a cleaner, more flexible design, in order to facilitate further research in weight optimisation. A description of the design is given, as well as experiments to compare performance with the previous implementation and to demonstrate extensibility.
Original languageEnglish
Pages (from-to)99-
Number of pages10
JournalPrague Bulletin of Mathematical Linguistics
Volume91
DOIs
Publication statusPublished - 2009

Fingerprint Dive into the research topics of 'Improved Minimum Error Rate Training in Moses'. Together they form a unique fingerprint.

Cite this