Enhancement of Target-Oriented Opinion Words Extraction with Multiview-Trained Machine Reading Comprehension Model

Table 6

Statistic of experiment datasets.

Dataset	Split	Sentences	Targets
14lap	Training	1158	1634
	Testing	343	482
14res	Training	1627	2643
	Testing	500	865
15res	Training	754	1076
	Testing	325	436
16res	Training	1079	1512
	Testing	329	457