Researchers at MIT have developed a system that can automatically update outdated and factually inconsistent data in Wikipedia articles.
The automated tool is able to save time spent by real-life editors by replacing information in sentences with accuracy while retaining human-like tone and grammar.
The researchers used two different databases containing structured sentences and relevant Wikipedia sentences, to train the AI system. As a result, it is now able to identify the redundant information then rewrite it without much human intervention.
Researchers feel that this tool will help editors save a lot of time and effort that goes in finding incorrect or outdated information. Darsh Shah, a PhD student in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and one of the lead authors of this said, “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,”.
He added “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 to inefficiency.”
Though there are other bots that monitor edits on Wikipedia, however, they are task-specific like dropping relevant info in a preset template or mitigating vandalism, the new one is far more competent.
While this tool outperforms other AI editors, it is not ready yet for a deployment. Independent human editors have given it a score of four out of five for accuracy and a score of three-and-a-half out of five for grammar accuracy.
Given its effectiveness in pointing out the incorrect data and the ability to replace it with factually correct and unbiased information makes it a perfect tool to aid editors and curb fake news.