A Structured Review of the Validity of BLEU

Ehud Reiter
2018 Computational Linguistics  
The BLEU metric has been widely used in NLP for over 15 years to evaluate NLP systems, especially in machine translation and natural language generation. I present a structured review of the evidence on whether BLEU is a valid evaluation technique-in other words, whether BLEU scores correlate with real-world utility and user-satisfaction of NLP systems; this review covers 284 correlations reported in 34 papers. Overall, the evidence supports using BLEU for diagnostic evaluation of MT systems
more » ... ich is what it was originally proposed for), but does not support using BLEU outside of MT, for evaluation of individual texts, or for scientific hypothesis testing.
doi:10.1162/coli_a_00322 fatcat:rfvawsrtxzboxozqwscte5yire