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

Table 4

Word segmentation performance on all learned words and sentences.

Method	Train data	Test data	Precision (%)	Recall (%)	F1-score (%)	IoU	Time (s/word)
Deepcut	Best train	Best train	97.42	97.89	97.65	0.95	1.50E − 03
THDICTSDR	Best train	Best train	99.20	99.55	99.48	0.99	0.03
THDICTSDR	LST train	LST train	98.36	99.69	99.37	0.98	0.03