Grouping business news stories based on salience of named entities

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review


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.
Titel på värdpublikation15th Conference of the European Chapter of the Association for Computational Linguistics : Proceedings of Conference, Volume 1: Long Papers
Antal sidor11
UtgivningsortStroudsburg, PA
FörlagThe Association for Computational Linguistics
ISBN (elektroniskt)978-1-945626-34-0
StatusPublicerad - 2017
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangConference of the European Chapter of the Association for Computational Linguistics - Valencia, Spanien
Varaktighet: 3 apr. 20177 apr. 2017
Konferensnummer: 15


  • 113 Data- och informationsvetenskap

Citera det här