@InProceedings{song-lee:2017:EACLshort,
  author    = {Song, Yan  and  Lee, Chia-Jung},
  title     = {Learning User Embeddings from Emails},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {733--738},
  abstract  = {Many important email-related tasks, such as email classification or search,
	highly rely on building quality document representations (e.g., bag-of-words or
	key phrases)  to assist matching and understanding. 
	Despite prior success on representing textual messages, creating quality user
	representations from emails was overlooked. In this paper, we propose to 
	represent users using embeddings that are trained to reflect the email
	communication network. Our experiments on Enron dataset suggest that the
	resulting embeddings capture the semantic distance between users. To assess the
	quality of embeddings in a real-world application, we carry out  auto-foldering
	task where the lexical representation of an email is enriched with user
	embedding features. Our results show that folder prediction accuracy is
	improved when embedding features are present across multiple settings.},
  url       = {http://www.aclweb.org/anthology/E17-2116}
}