Content Deduplication with Granularity Tweak Based on Base and Deviation for Large Text Dataset

Table 4

NLP vs. non-NLP.

Methods	ROUGE-1	ROUGE-2	F-measure
Ranking [36]	0.38613	0.06918	0.42246
COSUM [37]	0.34124	0.09678	0.44365
NLP	0.43219	0.10642	0.46596