Data-Driven News Generation for Automated Journalism

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

Despite increasing amounts of data and ever improving natural language generation techniques, work on automated journalism is still relatively scarce. In this paper, we explore the field and challenges associated with building a journalistic natural language generation system. We present a set of requirements that should guide system design, including transparency, accuracy, modifiability and transferability. Guided by the requirements, we present a data-driven architecture for automated journalism that is largely domain and language independent. We illustrate its practical application in the production of news articles upon a user request about the 2017 Finnish municipal elections in three languages, demonstrating the successfulness of the data-driven, modular approach of the design. We then draw some lessons for future automated journalism.
Originalspråkengelska
Titel på gästpublikationThe 10th International Natural Language Generation conference, Proceedings of the Conference
Antal sidor10
UtgivningsortStroudsburg
FörlagThe Association for Computational Linguistics
Utgivningsdatum4 sep 2017
Sidor188-197
ISBN (tryckt)978-1-945626-52-4
DOI
StatusPublicerad - 4 sep 2017
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangInternational Conference on Natural Language Generation - Tilburg, Holland
Varaktighet: 5 nov 20188 nov 2018
Konferensnummer: 11
https://inlg2018.uvt.nl/

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap

Citera det här