The NIST 2008 Metrics for Machine Translation Challenge - Overview, Methodology, Metrics, and Results

Published

March 10, 2010

Author(s)

Mark A. Przybocki, Kay Peterson, P. S. Bronsart, Gregory A. Sanders

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. The general classes of metrics that were evaluated are summarized. 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 at the sentence, document, and system level with results conditioned by various properties of the test data. This paper concludes with some perspective on the improvements that should be incorporated into future evaluations of metrics for MT evaluation.

Citation

Machine Translation

Pub Type

Journals

Download Paper

Local Download

Keywords

MT metrics, evaluation, automated metrics, machine translation, MT, MetricsMATR

Citation

Przybocki, M. , Peterson, K. , Bronsart, P. and Sanders, G. (2010), The NIST 2008 Metrics for Machine Translation Challenge - Overview, Methodology, Metrics, and Results, Machine Translation, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=903840 (Accessed December 8, 2024)