MIT Press

Table 6

Summary of statistics for the COCO image data set.

	Tokens	Vocab.	Vocabulary Population		Long Memory
	Tokens	Vocab.	Zipf’s Law f(r) ∝ r^−α	Heaps’ Law v(n) ∝ n^β	Ebeling’s Method m(l) ∝ l^η	Taylor’s Law σ ∝ μ^ζ	Long Range Correlation c(s) ∝ s^−ξ
Image COCO (English, collection of image caption)
original data set	105,933	6,095	Yes	0.76 (0.09)	0.99 (0.03)	0.50 (0.04)	No

	Tokens	Vocab.	Vocabulary Population		Long Memory
	Tokens	Vocab.	Zipf’s Law f(r) ∝ r^−α	Heaps’ Law v(n) ∝ n^β	Ebeling’s Method m(l) ∝ l^η	Taylor’s Law σ ∝ μ^ζ	Long Range Correlation c(s) ∝ s^−ξ
Image COCO (English, collection of image caption)
original data set	105,933	6,095	Yes	0.76 (0.09)	0.99 (0.03)	0.50 (0.04)	No