@InProceedings{mckelvey-EtAl:2017:SocialNLP2017,
  author    = {McKelvey, Kevin  and  Goutzounis, Peter  and  da Cruz, Stephen  and  Chambers, Nathanael},
  title     = {Aligning Entity Names with Online Aliases on Twitter},
  booktitle = {Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {25--35},
  abstract  = {This paper presents new models that automatically align online aliases with
	their real entity names. Many research applications rely on identifying entity
	names in text, but people often refer to entities with unexpected nicknames and
	aliases. For example, The King and King James are aliases for Lebron James, a
	professional basketball player. Recent work on entity linking attempts to
	resolve mentions to knowledge base entries, like a wikipedia page, but linking
	is unfortunately limited to well-known entities with pre-built pages. This
	paper asks a more basic question: can aliases be aligned without background
	knowledge of the entity? Further, can the semantics surrounding alias mentions
	be used to inform alignments? We describe statistical models that make
	decisions based on the lexicographic properties of the aliases with their
	semantic context in a large corpus of tweets. We experiment on a database of
	Twitter users and their usernames, and present the first human evaluation for
	this task. Alignment accuracy approaches human performance at 81%, and we show
	that while lexicographic features are most important, the semantic context of
	an alias further improves classification accuracy.},
  url       = {http://www.aclweb.org/anthology/W17-1104}
}