News Classification and Entity Extraction
The challenge
Newsrooms and archives publish and store huge numbers of articles. Tagging them by topic, people, and organisations by hand is slow and inconsistent.
What we built
We built a news classification and clustering system that sorts articles into categories, groups related stories, and extracts the names of people, organisations, and places.
Editors get consistent tags at scale, readers get better search and recommendations, and the archive becomes a real asset. The system has been demonstrated in an operational setting.
Business value
- Consistent tagging at scale
- Better search, recommendations, and archive value
- Editorial time freed from manual tagging
- Related stories grouped automatically
Where else it applies
The same approach transfers to legal, research, corporate communications, and government. It belongs to our Document and Knowledge AI work: software that reads, sorts, and answers questions from documents, so teams stop searching and re-entering information by hand.
Task
Tag and group news content at scale, consistently.
Let’s build together
Got a deep-tech challenge?
Tell us the problem. We’ll show you the closest thing we have already built and how we would adapt it to your data.
Tell us what you’re working on