Improving Search Results
- by Antoniy Yushkevych
- in IT News
A few months ago, Google announced what they believe to be their most important search engine update in the last five years. This update got named BERT and it impacts 10% of search queries by using new neural networking techniques to better understand users’ intentions behind their queries.
According to Google, this update will mainly impact complex searches that depend on context. BERT stands for Bidirectional Encoder Representations from Transformers and is a deep learning algorithm related to natural language processing. Put simply, it helps the search engine better understand what words in a sentence mean, but with relevant context. Transformers are one of the more recent developments in machine learning. They work especially well for data where the sequence of elements is important, which obviously makes them a useful tool for working with natural language and thus, search queries.
There are plenty of words in the English language that are spelled letter-for-letter but have absolutely different meanings when the context is taken into account. Bert is designed to help solve ambiguous sentences and phrases that are made up of many words with multiple meanings.
Here’s an example of how Google is able to understand a query more like a human and thus show a more relevant result.
Please note: this example is for demonstrative purposes and might not reflect actual search results when the said query is entered.
Ideally, this update means that the popular search engine will now be able to better understand what exactly you are looking for and provide you with more relevant search results.
There are plenty of myths, confusion and link baiting surrounding BERT algorithm. Here are a few to watch out for:
Myth 1: BERT impacts your page’s SEO.
Since the BERT algorithm helps Google analyze users’ search queries, not web pages, it should have little to no effect on websites’ SEO. This doesn’t mean, however, that you should forget about SEO in general.
Myth 2: BERT is the biggest update of all time.
Although it is definitely a great leap forward for Google, as per their press release statement:
“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.”
Some other candidates for this position include the Hummingbird update and the Caffeine update.
Myth 3: BERT has a small effect on search results.
Despite Google’s statement, there are certain individuals promoting that this algorithm is not particularly significant. Affecting 1 in 10 of all searches in the English language, however, makes for a quite important update in our eyes.