Research on Uyghur-Chinese Neural Machine Translation Based on the Transformer at Multistrategy Segmentation Granularity

Table 1

Corpus data at different granularities.

Different granularity	Training set		Test set
	Number of sentences	Average sentence length	Number of sentences	Average sentence length
Syllable	147434	81.58	1000	46.21
Marked syllable	147434	81.65	1000	46.36
Words	147434	82.64	1000	46.97
Syllable word fusion	147434	99.69	1000	57.35