Search results on Google Search have significantly improved in the last decades; but surely there are rooms for improvement. Things, however, are going to get even better with a major update announced by the search engine giant on Friday. The update, which perhaps, is the most significant in the last couple of years, will improve how natural results are presented.
Underlining how search queries over the years have transformed and how Google has been able to improve Search to meet the heavy demands from users, the company explained why it is important to improve on understanding of natural search queries. This will be achieved by applying a neural network-based technique known as Bidirectional Encoder Representations from Transformers or BERT for short. BERT according to Google, “enables anyone to train their own state-of-the-art question answering system.”
“With the latest advancements from our research team in the science of language understanding–made possible by machine learning–we’re making a significant improvement to how we understand queries, representing the biggest leap forward in the past five years, and one of the biggest leaps forward in the history of Search.”
The change was prompted by acknowledging how Search’s language understanding capabilities are still prone to failures, especially when they are complex. “In fact, that’s one of the reasons why people often use “keyword-ese,” typing strings of words that they think we’ll understand, but aren’t actually how they’d naturally ask a question.”
So, how does BERT works? According to Google, this “breakthrough came as a result of research on transformers: modes that process words in relation to all the other words in a sentence, rather than one-by-one in order.” BERT’s role will be to consider full context of a word by looking at the words that come before and after it. This is important when it comes to understanding the intent behind such search queries.
So, what do you get from all these changes? Here is Google’s Fellow and Vice President, Search Pandu Nayak in a blog post:
“Well, by applying BERT models to both ranking and featured snippets in Search, we’re able to do a much better job helping you find useful information. In fact, when it comes to ranking results, BERT will help Search better understand one in 10 searches in the U.S. in English, and we’ll bring this to more languages and locales over time.”
A couple of months ago, Google added the ability to let you auto-delete your activity logs. The search engine behemoth launched auto-delete controls for location history and web/app activity logs. The features will allow users to select one of two windows-three months or 18 months, which specifies exactly how long they would like to retain data. This can be done from within the Google Account dashboard on both mobile and the web, where a dropdown menu allows them to choose any of the two options.