Thai Word Segmentation with a Brain-Inspired Sparse Distributed Representations Learning Memory

Table 2

Word-level performance comparison on LST20.

Method	Train data	Test data	Precision (%)	Recall (%)	F1-score (%)	IoU	Time (s/word)
Longest	Train	Test	80.60	72.06	76.09	0.61	4.20E − 05
Newmm	Train	Test	83.28	73.76	74.77	0.64	7.45E − 06
Deepcut	Train	Test	96.67	97.13	96.90	0.94	1.50E − 03
THDICTSDR	Train	Test	94.42	96.85	95.62	0.92	0.028