Google is about to get a lot better at understanding your search queries
The biggest upgrade in five years
Google has announced its rolling out a major upgrade to its search engine, which should mean it gets better at understanding your queries in context – rather than just matching keywords, it'll actually figure out what you're trying to say.
Thanks to a new machine learning process, Google says, you won't have to try and stuff your searches with keywords to try and get the right results up first. Instead, you can be more natural and conversational.
"Particularly for longer, more conversational queries, or searches where prepositions like 'for' and 'to' matter a lot to the meaning, Search will be able to understand the context of the words in your query," says Google's Pandu Nayak.
- Google just launched the Pixelbook Go
- Android customizations could hurt it
- Facebook is getting into news
"No matter what you’re looking for, or what language you speak, we hope you’re able to let go of some of your keyword-ese and search in a way that feels natural for you," adds Nayak.
Seek and you will find
Let's give you some of Google's examples to show how the changes work. Previously, in a "2019 brazil traveler to usa need a visa" search, Google would ignore the "to" because it's so common, and return results for US citizens going to Brazil. Now it recognizes the "to" and that the query is about travelers going from Brazil to the US.
On a search like "do estheticians stand a lot at work", Google previously wouldn't understand the context "stand" was used in (i.e. relating to the physical demands of the job). With the new update, it'll realize what you're trying to say.
These improvements are substantial enough that Google is calling this its most important search upgrade in five years. To begin with the new technology is only being applied to searches in US English, but it will expand to more languages over time.
Get the best Black Friday deals direct to your inbox, plus news, reviews, and more.
Sign up to be the first to know about unmissable Black Friday deals on top tech, plus get all your favorite TechRadar content.
For a more detailed look at the neural network innovations underpinning this improvement – specifically a training model called Bidirectional Encoder Representations from Transformers or BERT – head over to Google's blog post on the changes.
Dave is a freelance tech journalist who has been writing about gadgets, apps and the web for more than two decades. Based out of Stockport, England, on TechRadar you'll find him covering news, features and reviews, particularly for phones, tablets and wearables. Working to ensure our breaking news coverage is the best in the business over weekends, David also has bylines at Gizmodo, T3, PopSci and a few other places besides, as well as being many years editing the likes of PC Explorer and The Hardware Handbook.