id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_sqfox4ylnzcxfbetwox2eu5t2q	Polina Kuznetsova	TreeTalk: Composition and Compression of Trees for Image Descriptions	2014	12	.pdf	application/pdf	11841	1505	69	TREETALK: Composition and Compression of Trees for Image Descriptions free text on web pages, to textual descriptions directly describing depicted image content (i.e. captions). Figure 1: Harvesting phrases (as tree fragments) for the target image based on (partial) visual match. useful bits of text (as tree fragments) from existing image descriptions using detected visual content and propose a tree compression algorithm that performs a light-weight parsing to search for the optimal set of tree branches to prune. Our work results in an improved image caption corpus with automatic generalization, which is publicly available.1 As illustrated in Figure 1, for a query image detection, we extract four types of phrases (as tree Figure 2 shows a simplified example of a composed sentence with its corresponding parse structure. scores (log probabilities) estimated from the 1M image caption corpus (Ordonez et al., 2011) parsed using the Stanford parser (Klein and Manning, 2003).	./cache/work_sqfox4ylnzcxfbetwox2eu5t2q.pdf	./txt/work_sqfox4ylnzcxfbetwox2eu5t2q.txt