id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_nj6cpocaafedndn4c5yt5dstbu	Andrew Chisholm	Entity Disambiguation with Web Links	2015	12	.pdf	application/pdf	7238	742	62	names and web pages that link to Wikipedia; (3) detailed development experiments, including analysis they learn entity representations based on similarity between link contexts and article text in Wikipedia. models derived from popularity metrics; alias models derived from Wikipedia redirects, disambiguation pages and inter-article links; textual context On the CoNLL development data, BOW context derived from Wikipedia article text achieves 50.6 p@1. We also build entity models from their mention contexts, i.e., the combined text surrounding all incoming links. Refer back to Table 2 for p@1 results for individual Web link components on the development data. Table 5 compares Wikipedia and Wikilinks coverage of entities from the CoNLL development set. The article, mention and web link models each attain their best performance with all component features (entity, name, BOW, and DBOW): 84.7, 81.1, Adding mention context features doesn't improve the more conventional Wikipedia article model. replace Wikipedia derived data in entity linking.	./cache/work_nj6cpocaafedndn4c5yt5dstbu.pdf	./txt/work_nj6cpocaafedndn4c5yt5dstbu.txt