Unsupervised Quality Estimation Model for English to German Translation and Its Application in Extensive Supervised Evaluation

Table 10

The performances on WMT13 shared tasks using Pearson correlation.

System	Correlation score with human judgments
	Other-to-English						English-to-other
	CS-EN	DE-EN	ES-EN	FR-EN	RU-EN	Mean	EN-CS	EN-DE	EN-ES	EN-FR	EN-RU	Mean
hLEPOR	0.81	0.96	0.90	0.96	0.71	0.87	0.76	0.94	0.91	0.91	0.77	0.86
nLEPOR𝐴	0.80	0.94	0.94	0.96	0.69	0.87	0.82	0.92	0.90	0.92	0.68	0.85
METEOR	0.99	0.96	0.97	0.98	0.84	0.95	0.82	0.88	0.88	0.91	0.55	0.81
BLEU	0.89	0.91	0.94	0.94	0.60	0.86	0.80	0.82	0.88	0.90	0.62	0.80
TER	0.77	0.87	0.91	0.93	0.80	0.80	0.70	0.73	0.78	0.91	0.61	0.75

Bold fonts mean the best performance.