BBC News website extends its use of artificial intelligence in semi-automated journalism, leveraging Arria NLG to help publish localized election news and results for each of the United Kingdom’s 690 constituencies minutes after votes are declared
MORRISTOWN, New Jersey, Dec. 17, 2019 /PRNewswire/ — Arria NLG today reported that the BBC News website, through its Semi-Automatic Local Content (Salco) project, extended its use of Arria’s Natural Language Generation (NLG) platform to automate the production of news coverage of the recent elections in the United Kingdom (UK).
BBC News Labs’ goal was to expand its ability to publish regionally tailored stories that contained local statistics and results for each of its subscribers on election night. With Arria NLG, the media giant achieved its objective and successfully published hundreds of articles, presenting provincial data for each demographic on one of the busiest news nights in UK history.
Arria NLG is a type of artificial intelligence that transforms data into insightful written or spoken language. In advance of the election, BBC journalists built a myriad of story templates within Salco using Arria NLG Studio that covered all possible scenarios and outcomes following the polls’ close on Thursday 12 December. Results were automatically processed using Arria to produce contextual voice and text articles for every constituency which, prior to publication, were edited by BBC journalists.
With Arria NLG, the BBC published 689 local stories, 100,000 words in 10 hours, delivering real-time election results for each of the country’s 690 constituencies. The speed and accuracy with which Arria’s NLG technology automates the production of local versions of news stories empowers editors and journalists working in hectic, deadline-driven environments to scale their production and deliver exponentially more coverage to local markets.
In a recent interview, David Caswell, BBC News Labs, addressed the value NLG provides to both the BBC and its readers, commenting that, “Natural Language Generation systems like Salco can unlock rich and relevant stories contained in public datasets for everyone across the UK. These local stories, told in a language, style and tone that make them accessible to local audiences, can include more people in the data-driven debates that were previously open only to those who knew where to find the data.” Read full interview
“This is about doing journalism that we cannot do with human beings at the moment,” said Robert McKenzie, editor of BBC News Labs. “Using machine assistance, we generated a story for every single constituency that declared last night with the exception of the one that hasn’t finished counting yet. That would never have been possible [using humans].”
“We are honored to work with BBC News, one of the world’s most widely-respected media companies,” said Sharon Daniels, CEO of Arria NLG. “What the BBC News team accomplished on election night is an historic milestone for media worldwide. This successful use-case proves how natural language technology transforms the way people work by extracting insights from data to tell a more complete story.
“The Arria NLG Studio platform combines advanced language analytics and computational linguistics together to transform data directly into insightful, explanatory narratives that are relevant to the audience receiving the information.”
About Arria NLG
Arria NLG is the global leader in the field of Natural Language Generation (NLG), a form of artificial intelligence specializing in extracting insights from complex data sources and communicating that information in natural language (i.e. as if written or spoken by a human). The company owns, develops and licenses its technology through its Arria NLG Studio Platform. For additional information, please visit https://www.arria.com/.
Contact: Lyndsee Manna, SVP Business Development, +1 973 534 9478 or via email firstname.lastname@example.org
The content is by PR NewsWire. DKODING Media is not responsible for the content provided or any links related to this content. DKODING Media is not responsible for the correctness, topicality or the quality of the content.