KoRASA: Pipeline Optimization for Open-Source Korean Natural Language Understanding Framework Based on Deep Learning

Table 6

Featurization.

Model	Intent classification				Entity extraction
	Train		Test		Train		Test
	Acc	F1	Acc	F1	Acc	F1	Acc	F1
Regex + LS + CV	1.000	1.000	0.980	0.980	0.988	0.089	0.949	0.882
Regex	1.000	1.000	0.980	0.978	0.993	0.989	0.959	0.902
CV	1.000	1.000	0.980	0.985	0.993	0.989	0.959	0.905