Blog & News

Arria NLG Technology Expands BBC’s Coverage of Recent UK Elections

By Arria NLG Team | December 17, 2019

As reported in Yahoo! Finance today, the BBC News website has extended 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 650 constituencies minutes after the votes were declared.

The BBC is the world’s leading public service broadcaster. 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 650 constituencies. Forty of the constituencies also received stories in Welsh. 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.

According to Robert McKenzie, editor of BBC News Labs, “This is about doing journalism that we cannot do with human beings at the moment. 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 human journalists].”

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 [the BBC’s Semi-Automatic Local Content project] 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.”