MIT develops AI tech to edit outdated Wikipedia articles

The technology uses machine learning to automatically spot and replace information, with the goal of aiding human editors

Artificial intelligence technology could be used to re-write outdated Wikipedia articles, reducing the workload for human editors, thanks to a system developed by Massachusetts Institute of Technology (MIT).  

Bots have been used to edit Wikipedia in the past, but while AI systems are now capable of generating text and can check facts, they aren’t always the most capable and often struggle to mimic the tone of human writers. 

By training its system on two databases, one with pairs of sentences and another with a relevant Wikipedia sentence, the researchers at MIT were able to train an AI system that can find outdated text in Wikipedia pages and then rewrite the passages in a human-like fashion. 

The AI system works by looking at new or updated information typed into the user interface in an unstructured sentence; one without grammar or style. The algorithm then finds the relevant Wikipedia entry, pinpoints the section the updated information is referencing and then rewrites the sentence with amended details in a human-like fashion.

The idea is that the AI removed the need for human editors to laboriously search through and amend Wikipedia entries.

Related Resource

Diversity in the digital workplace

The future of work is a collaborative effort between humans and robots

Download now

“There are so many updates constantly needed to Wikipedia articles. It would be beneficial to automatically modify exact portions of the articles, with little to no human intervention,” says Darsh Shah, a PhD student in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and one of the lead authors of a paper detailing the AI research. “Instead of hundreds of people working on modifying each Wikipedia article, then you’ll only need a few, because the model is helping or doing it automatically. That offers dramatic improvements in efficiency.”

The AI can also help identify so-called ‘fake news’ as it has been trained to recognise the difference between legitimate additions to a Wikipedia entry and information that is factually incorrect. The system seeks evidence and other information to ascertain if such a claim is true or false. 

The system is not ready for full use on Wikipedia just yet, as it has been given a score of four out of five for accuracy by human editors and a score of three-and-a-half out of five for gramma accuracy. As such, it outperforms other AI tools but isn’t quite able to mimic human editors just yet. 

However, it is a sign of the continued development and refinement of AI technology and how it can be used to make life easier for humans rather than replace them, thus enshrining the ideals of digital transformation.

Featured Resources

2021 Thales access management index: Global edition

The challenges of trusted access in a cloud-first world

Free download

Transforming higher education for the digital era

The future is yours

Free download

Building a cloud-native, hybrid-multi cloud infrastructure

Get ready for hybrid-multi cloud databases, AI, and machine learning workloads

Free download

The next biggest shopping destination is the cloud

Know why retail businesses must move to the cloud

Free Download

Recommended

Build trustworthy AI with MLOps
Whitepaper

Build trustworthy AI with MLOps

15 Oct 2021
Alation acquires data insights firm Lyngo Analytics
Acquisition

Alation acquires data insights firm Lyngo Analytics

15 Oct 2021
The business value of MLOps
Whitepaper

The business value of MLOps

15 Oct 2021
The AI-powered supply chain
Whitepaper

The AI-powered supply chain

15 Oct 2021

Most Popular

Best Linux distros 2021
operating systems

Best Linux distros 2021

11 Oct 2021
Apple MacBook Pro 15in vs Dell XPS 15: Clash of the titans
Laptops

Apple MacBook Pro 15in vs Dell XPS 15: Clash of the titans

11 Oct 2021
Apple iPad (2021) review: The best entry-level iPad
tablets

Apple iPad (2021) review: The best entry-level iPad

12 Oct 2021