Microsoft announced their next AI model, a large-scale sparse model that complements our production Transformer models, they are calling MEB or “Make Every Feature Binary.” Microsoft said this makes the search results on Bing more relevant.
In fact, MEB is running in production for 100 percent of Bing searches, in all regions and languages.
How, well, Microsoft said “to make search more accurate and dynamic, MEB better harnesses the power of large data and allows for an input feature space with over 200 billion binary features that reflect the subtle relationships between search queries and documents.” George at Search Engine Land has an easier to understand version of all of this over here.
Microsoft said MEB assigns each fact to a feature, “so it can assign weights that distinguish between the ability to fly in, say, a penguin and a puffin. It can do this for each of the characteristics that make a bird—or any entity or object for that matter—singular. Instead of saying “birds can fly,” MEB paired with Transformer models can take this to another level of classification, saying “birds can fly, except ostriches, penguins, and these other birds.””
How smart is MEB? Well it went through a lot of training. MEB is trained with more than 500 billion query/document pairs from three years of Bing searches. The input feature space has more than 200 billion binary features, Microsoft said.
Microsoft said the MEB model also demonstrates interesting capabilities to learn beyond semantic relationships. When looking into the top features learned by MEB, Microsoft found it can learn hidden intents between query and document.
It matters and improves search, Microsoft shared these data points:
- An almost 2 percent increase on clickthrough rate (CTR) on the top search results. Those results found “above the fold” without the need to scroll down.
- A reduction in manual query reformulation by more than 1 percent. Users needing to manually reformulate queries means they didn’t like the results they found with their original query.
- A reduction of clicks on pagination by over 1.5 percent. Users needing to click on the “next page” button means they didn’t find what they were looking for on the first page.
Want to geek out on this? Read the Microsoft blog post.
And of course, I still have to share my pun again, even though it didn’t make the cut in the final edit. https://t.co/6UckEEeh3f
— Frédéric Dubut (@CoperniX) August 4, 2021
Forum discussion at Twitter.