Press coverage "Evaluating named entity recognition tools for extracting social networks from novels"

Media contributions

• Title	Offbeat: Why language technology can’t handle Game of Thrones (yet)
  Degree of recognition	International
  Media name/outlet	Tunise Soir News
  Media type	Online journalism
  Date	18/04/2019
  Description	Researchers from the Vrije Universiteit Amsterdam and the Dutch Royal Academy’s Humanities Cluster evaluated four state-of-the-art tools for recognising names in text, to assess and improve their performance on popular fiction. They find solutions to boost the tools’ capability to recognise names in one novel from an accuracy of 7% to 90%.
  URL	www.tunisiesoir.com/top-news/offbeat-why-language-technology-cant-handle-game-of-thrones-yet-15530-2019/
  Persons	Marieke van Erp

• Title	What are natural language processing tools? How can they be used on novels and Game of Thrones?
  Degree of recognition	International
  Media name/outlet	Scitech EUROPA
  Media type	Online journalism
  Date	18/04/2019
  Description	What are natural language processing tools? A new study has analysed how they can be used to create social networks out of literary works including Game of Thrones.
  URL	https://www.scitecheuropa.eu/natural-language-processing/94442/
  Persons	Marieke van Erp

• Title	Game of Thrones: Why Language Technology cannot handle it (Yet)
  Degree of recognition	International
  Media name/outlet	Science Times
  Media type	Online journalism
  Date	18/04/2019
  Description	The evaluation researchers from Vrije Universiteit Amsterdam and the Humanities Cluster of Dutch Royal Academy was done on four state-of-the-art tools for recognizing names in the text, to assess and improve their performance on popular fiction. They discovered solutions to boost the capacity of the machines in understanding names in one novel from the accuracy of seven percent to 90 percent.
  URL	https://www.sciencetimes.com/articles/20393/20190418/game-of-thrones-why-language-technology-cannot-handle-it-yet.htm
  Persons	Marieke van Erp

• Title	Language detecting technology struggles with George R. R. Martin's Game of Thrones because the bizarre names don't behave 'normally'
  Degree of recognition	International
  Media name/outlet	Daily Mail
  Media type	Online journalism
  Country/Territory	United Kingdom
  Date	18/04/2019
  Description	Quirky names, such as Daenerys, don't look or resemble most names Algorithms are developed and trained to detect names by studying newspapers A vastly different writing style is found in non-fiction novels and makes them hard to detect
  URL	https://www.dailymail.co.uk/sciencetech/article-6937427/Language-detecting-technology-struggles-George-R-R-Martins-Game-Thrones.html
  Persons	Marieke van Erp

• Title	Why language technology can't handle Game of Thrones (yet)
  Degree of recognition	International
  Media name/outlet	Science Daily
  Media type	Online journalism
  Date	18/04/2019
  Description	Researchers have performed a thorough evaluation of four different name recognition tools on popular 40 novels, including A Game of Thrones. Their analyses highlight types of names and texts that are particularly challenging for these tools to identify as well as solutions for mitigating this.
  URL	https://www.sciencedaily.com/releases/2019/04/190418080816.htm
  Persons	Marieke van Erp

• Title	Why language technology can't handle Game of Thrones (yet)
  Degree of recognition	International
  Media name/outlet	Tech Xplore
  Media type	Online journalism
  Date	18/04/2019
  Description	Researchers from the Vrije Universiteit Amsterdam and the Dutch Royal Academy's Humanities Cluster evaluated four state-of-the-art tools for recognising names in text, to assess and improve their performance on popular fiction. They find solutions to boost the tools' capability to recognise names in one novel from an accuracy of 7% to 90%.
  URL	https://techxplore.com/news/2019-04-language-technology-game-thrones.html
  Persons	Marieke van Erp

• Title	PRESS RELEASE: Why language technology can’t handle Game of Thrones (yet)
  Degree of recognition	International
  Media name/outlet	PeerJ Press room
  Media type	Other
  Date	18/04/2019
  Description	Researchers from the Vrije Universiteit Amsterdam and the Dutch Royal Academy’s Humanities Cluster evaluated four state-of-the-art tools for recognising names in text, to assess and improve their performance on popular fiction. They find solutions to boost the tools’ capability to recognise names in one novel from an accuracy of 7% to 90%.
  URL	https://d2pdyyx74uypu5.cloudfront.net/pressReleases/2019/04/Press-Release-LanguageTechGOT.pdf
  Persons	Marieke van Erp