, Volume 24, Issue 1, pp 51-65
Date: 20 Apr 2010

Significance tests of automatic machine translation evaluation metrics

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Automatic evaluation metrics for Machine Translation (MT) systems, such as BLEU, METEOR and the related NIST metric, are becoming increasingly important in MT research and development. This paper presents a significance test-driven comparison of n-gram-based automatic MT evaluation metrics. Statistical significance tests use bootstrapping methods to estimate the reliability of automatic machine translation evaluations. Based on this reliability estimation, we study the characteristics of different MT evaluation metrics and how to construct reliable and efficient evaluation suites.