A Study on Chinese-English Machine Translation Based on Transfer Learning and Neural Networks

Table 4

Experimental results of the recurrent neural network-based monolingual to machine translation quality assessment model under joint training conditions.

Method	Data	Pearson’s	MAE	RMSE
Transformer+embedding+fine-tuning	Dev	0.4028	0.1325	0.1857
	Test2016	0.4146	0.1328	0.1539
	Test2017	0.4146	0.1382	0.1759
Transformer+latent+fine-tuning	Dev	0.6414	0.1167	0.1611
	Test2016	0.6471	0.1028	0.1325
	Test2017	0.6201	0.1124	0.1348
Transformer+wordpredicting+fine-tuning	Dev	0.7065	0.0795	0.1277
	Test2016	0.774	0.0894	0.1578
	Test2017	0.6857	0.1101	0.1258