What Is BERT in Search?

It’s more popularly known as a Google search algorithm ingredient /tool/framework called Google BERT which aims to help Search better understand the nuance and context of words in Searches and better match those queries with helpful results.

BERT has dramatically accelerated natural language understanding NLU more than anything and Google’s move to open-source BERT has probably changed natural language processing forever.  More info:  Open Sourcing BERT: State-of-the-Art Pre-training for Natural Language Processing

Rolling out.

BERT started rolling out in October 2019 and is fully live now. It is rolling out for English language queries now and will expand to other languages in the future.

Featured Snippets.

This will also impact featured snippets. Google said BERT is being used globally, in all languages, on featured snippets.

It was opened-sourced last year and written about in more detail on the Google AI blog. In short, BERT can help computers understand the language a bit more as humans do.

When is BERT Google search used?

Google said BERT helps better understand the nuances and context of words in searches and better match those queries with more relevant results. It is also used for featured snippets, as described above. Using Natural Language Processing (NLP), BERT helps the search engine understand the significance of words like “to” or “for” (transformer words) in the context of a search. These would have been previously ignored by the search engine, leading to frustrating goose chases while someone tried to find the right combination of words or phrases.

For example, before BERT, Google results for “math practice books for adults” would have included hits that – while technically keyword matches – were irrelevant:

Source: Google

By emphasizing transformer words, the search engine can now understand that “for” is an important part of the sentence grammatically. Previously, it would have ignored the word, returning results involving math books for any demographic with the adult in the term – such as young adults.

Google BERT doesn’t change any rules for keywords and the update didn’t change any of the metrics the search engine uses for determining page rank. Nonetheless, it’s still going to have a pretty big impact on site traffic and page ranks.

In one example, Google said, with a search for “2019 brazil traveler to usa need a visa,” the word “to” and its relationship to the other words in query are important for understanding the meaning. Previously, Google wouldn’t understand the importance of this connection and would return results about U.S. citizens traveling to Brazil. “With BERT, Search is able to grasp this nuance and know that the very common word “to” actually matters a lot here, and we can provide a much more relevant result for this query,” Google explained.

Note: The examples below are for illustrative purposes and may not work in the live search results.

Featured snippet example.

Here is an example of Google showing a more relevant featured snippet for the query “Parking on a hill with no curb”. In the past, a query like this would confuse Google’s systems. Google said, “We placed too much importance on the word “curb” and ignored the word “no”, not understanding how critical that word was to appropriately responding to this query. So we’d return results for parking on a hill with a curb.”

Source

TEXT / IMAGES / CURATED CONTENT

What You Need to Know About Google’s New Algorithm

Welcome BERT: Google’s latest search algorithm to better understand natural language

Google BERT Update

Will Google’s BERT change SEO Forever, Again?