Translation systems are generally trained to optimize BLEU, but many alternative metrics are available. We explore how optimizing toward various automatic evaluation metrics (BLEU...
Daniel Cer, Christopher D. Manning, Daniel Jurafsk...
In Minimum Error Rate Training (MERT), BLEU is often used as the error function, despite the fact that it has been shown to have a lower correlation with human judgment than other...
BLEU is the de facto standard for evaluation and development of statistical machine translation systems. We describe three real-world situations involving comparisons between diff...
David Chiang, Steve DeNeefe, Yee Seng Chan, Hwee T...
Confusion networks are a simple representation of multiple speech recognition or translation hypotheses in a machine translation system. A typical operation on a confusion network...