GOOGLE BERT: THE MACHINE LEARNING ALGORITHM

Google Bert has been recently added Among the long list of the algorithm updates of the world’s most famous search engine.  The main objective of Google remains the radical improvement of the experience of users searching on the internet.

It was officially launched on October 25th 2019, this new search algorithm – as stated Pandu Nayak on The Keyword blog – will enable Google “understanding searches better than ever before”, thanks to the developments of machine learning and the studies on languages comprehension. Through BERT, Bidirectional Encoder Representations from Transformers, SERP results are no longer obtained just on the basis of the combination of keywords.

HOW DOES GOOGLE BERT WORK?

Thanks to an Artificial Intelligence system, BERT is able to learn independently, starting from the analysis of millions of sentences written by humans and hundreds of books of all sorts. This accurate analysis, together with the speed of learning of BERT, allow the system to efficiently question answering, to understand the meaning of the search query typed by the user and also to develop complete meaning sentences (in this regard BERT solves the common sense test conceived by Allen Institute).

Google company stated: these improvements are oriented around improving language understanding, particularly for more natural language/conversational queries, as BERT is able to help Search better understand the nuance and context of words in Searches and better match those queries with helpful results. Particularly for longer, 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. You can search in a way that feels natural for you.”

The above image shows the search results for “2019 Brazil traveller to USA need a visa”. The previous algorithm gave unsatisfactory results, changing the sense of the user’s actual research intent, as it was based only on the keywords entered by the user. The reading or not of the prepositions, above all “to” and “for”, completely changes the meaning of a sentence and every word typed in the query are necessary to understand the needs of the users and to return results in line with their requests.  Previous Google search algorithms were not able to grasp these nuances.

GOOGLE ACHIEVEMENT

The company affirmed that GOOGLE BERT will impact 1 in 10 queries in terms of changing the SERP results. In fact, BERT represents the biggest change made since Google introduced RankBrain, a machine learning system, based on artificial intelligence, used to process Google research results and order them appropriately.

Vice President Pandu Nayak stated:

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.”

HOW WILL THE SEO CHANGE?

The expert Dawn Anderson explained that by Google BERT the SEO optimization can no longer be based only on the use of the keywords associated to the search.

The word -rose- means several things but it’s exactly the same word. The context must accompany the word otherwise the word means nothing.”

The new algorithm will analyse the results taking into account the context in which the keywords are used. These NLP Models will affect the SERP, especially with reference to those words that can have different meanings depending on the context in which they are inserted.

For more advices about SEO, visit our web page dedicated to optimisation.

Share this post:

Share on email
Share on facebook
Share on twitter
Share on linkedin
Share on whatsapp