@InProceedings{escoter-EtAl:2017:EACLlong,
  author    = {Escoter, Llorenc  and  Pivovarova, Lidia  and  Du, Mian  and  Katinskaia, Anisia  and  Yangarber, Roman},
  title     = {Grouping business news stories based on salience of named entities},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {1096--1106},
  abstract  = {In news aggregation systems focused on broad news domains, certain stories may
	appear in multiple articles. Depending on the relative importance of the story,
	the number of versions can reach dozens or hundreds within a day. The text in
	these versions may be nearly identical or quite different. Linking multiple
	versions of a story into a single group brings several important benefits to
	the end-user--reducing the cognitive load on the reader, as well as signaling
	the relative importance of the story. We present a grouping algorithm, and
	explore several vector-based representations of input documents: from a
	baseline using keywords, to a method using salience--a measure of importance
	of named entities in the text. We demonstrate that features beyond keywords
	yield substantial improvements, verified on a manually-annotated corpus of
	business news stories.},
  url       = {http://www.aclweb.org/anthology/E17-1103}
}