active

Live Page Translation

Aggregating multilingual live page content through automatic translations.

Aims

Machine translation can help BBC journalists tap into the local expertise of their colleagues and share it with their audiences.

Wherever a big story breaks somewhere in the world, the chances are the BBC is already running a “Live Page", providing a blow-by-blow account of developments in the local language, as well as in English.

Live Pages ensure our audiences are with us at every step of the news journey as events unfold. Our journalists monitor newswires and check coverage from around the BBC and beyond. They scan social media and keep in touch with the actors.

From all that information, they have to quickly synthesise and curate the most relevant information for their audiences, keeping coverage immediate, accessible and relevant.

It is a difficult, high-pressure role, where speed and accuracy are key; and it is further complicated by the multilingual nature of global news.

The BBC carries news in more than 40 languages. A BBC Hausa journalist might be monitoring news in Arabic, Turkish, Somali and Swahili to provide the breadth of coverage expected by their audiences. A BBC Russian journalist is likely to be looking at content in Azeri, Turkish and beyond.

This project aimed to bring those sources to them in their own language, to save them the trouble of manual searches and translation processes.

A richer outlook

Each of these teams would be reporting on the impact of a global event by building on multiple angles informed by local insight, experience and considerations. What if they could all contribute towards a richer tapestry by having a clear view of each other’s expertise, sources and perspectives?

Can machine translation help?

The first phase of the experimentation sought to bring machine-translated content to the publishing wellhead.

Auto-translated content from other language services appeared in the “drafts” column of our content management system. Our theory was that a journalist would see it, pick up the content and publish it.

That didn’t work out. The translation quality was not sufficient to put straight in front of audiences, and we were cluttering their screen with only semi-relevant content.

An internal newswire?

Journalists thought the translated content was interesting. They told us too that the translation quality was good enough for them to get the gist of what the story was about, even if it wasn’t accurate enough to put in front of audiences.

We took a step back and built a free-standing prototype that ingested, auto-translated and aggregated all our Live Page content.

For the first time ever, anyone in the BBC could see all of the Live Page content in one place. Users can now filter by language, or outlet, select the time frame and jump to the original language post.

The Hausa journalist mentioned above? She can now view Arabic, Turkish, Somali, Swahili updates from the past six, 12 or 24 hours.

She can get the gist of the story at a glance, and then decide whether she wants to further explore and utilise the information.

Results

  • There is a growing group of regular users who have told us that the prototype makes their lives simpler.
  • The tool has been particularly potent during big global events such as the Russia-Ukraine war, the protests in Iran or the crackdown in Myanmar where multiple outlets across the BBC turn to the local team for the latest.

Careers

Love data and code?

We're looking for talented developers to join our team.