The NIST 2008 Metrics for machine translation challenge—overview, methodology, metrics, and results

Entities Mentioned

• Gaithersburg
• Mark Przybocki

1. Abstract This paper discusses the evaluation of automated metrics developed for the purpose of evaluating machine translation (MT) technology. A general discussion of the usefulness of automated metrics is offered. The NIST MetricsMATR evaluation of MT metrology is described, including its objectives, protocols, participants, and test data. The methodology employed to evaluate the submitted metrics is reviewed. A summary is provided for the general classes of evaluated metrics. Overall results of this evaluation are presented, primarily by means of correlation statistics, showing the degree of agreement between the automated metric scores and the scores of human judgments. Metrics are analyzed ... (Read Full Article)

   Bookmark or Share this article

   
   

   Related Articles

   • Automatic Identification of Legal Terms in Czech Law Texts
   • also published in SpringerLink Home
   • ACL and Emnlp 2007 Report
   • also categorized in Machine Translation
   • What's the Use of a Crummy Translation?
   • also categorized in Machine Translation
   • Particle filtering versus beam search
   • also categorized in Machine Translation
   • 2006 ACL Lifetime Achievement Award
   • also categorized in Machine Translation

   • Translation out of English
   • also categorized in Machine Translation
   • Machine Translation links
   • also categorized in Machine Translation
   • Language Weaver: fast in translation
   • also mentions Mark Przybocki
   • EMNLP-CoNLL 2007 Call for Papers
   • also categorized in Machine Translation
   • Yahoo! Launches New Program to Advance Open-Source Software for ...
   • also categorized in Machine Translation

Login to comment.