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

Table 1

Word-level performance comparison on Best2010.

Method	Train data	Test data	Precision (%)	Recall (%)	F1-score (%)	IoU	Time (s/word)
Longest	Train	Test	77.01	67.05	71.68	0.56	3.95E − 05
Newmm	Train	Test	80.30	69.96	74.77	0.60	7.34E − 06
Deepcut	Train	Test	96.11	96.57	96.34	0.93	1.50E − 03
THDICTSDR	Train	Test	94.32	96.89	95.60	0.92	0.03