When Google fights spam with MUM and BERT – SEO and engine news – Abundance

An article published yesterday by Google explains how the latest two Google algorithms MUM and BERT weave their web to remove offensive or spammy results from the SERPs. The impact of artificial intelligence in search results should be even greater in the coming months…

google published an article yesterdayexplaining how Artificial Intelligence, and in particular the MUM and BERT algorithms, were used in its algorithms to fight spam and eliminate potentially offensive or dangerous content from search results.

Google takes the example of people in personal crisis and explains how the engine works in this case: ” Now, thanks to our latest AI model, MUM, we can automatically and more accurately detect a wider range of personal crisis searches. MUM can better understand the intent behind people’s questions to detect when someone is in need, helping us to more effectively show reliable and actionable insights at the right time. We will begin using MUM to make these improvements in the coming weeks. »

The aim is also to fight against pages presenting violent, shocking or inappropriate content: “ One of the ways to achieve this is the SafeSearch mode, which gives users the ability to filter out explicit results. This setting is on by default for Google Accounts for people under 18. And even when users choose to disable SafeSearch mode, our systems still reduce unwanted solicitation results for searches that aren’t looking for them. In fact, every day our security algorithms improve hundreds of millions of searches worldwide across web, image and video. But there’s still room for improvement, and we use advanced AI technologies like BERT to better understand what you’re looking for. BERT has given us a better understanding of whether searches are actually looking for explicit content, which helps us significantly reduce the chances of encountering surprising search results. This is a complex challenge that we have been tackling for some time, but in the last year alone, this improvement in BERT has resulted in a 30% reduction in unexpected shocking results. It has proven particularly effective in reducing explicit search content related to ethnicity, sexual orientation and gender, which can disproportionately impact women, especially women of color. »

And the article continues on MUM: MUM can transfer its knowledge in the 75 languages ​​it was trained in, which can help us extend security protections around the world much more efficiently. When we train a MUM model to perform a task – like classifying the nature of a query – it learns to do so in all the languages ​​it knows. »

And in particular the use of MUM in the context of the fight against spam and Black Hat practices: ” For example, we use AI to reduce unnecessary and sometimes dangerous spam pages in your search results. In the coming months, we will be using the MUM to improve the quality of our spam protections and to expand to languages ​​for which we have very little training data. We will also be able to better detect personal crisis queries around the world, working with trusted local partners to display actionable insights in several additional countries. »

When we know that Google discovers 40 billion spam pages every day, we can say that we have not finished seeing MUM and BERT weaving their respective webs in the algorithms of the Google search engine…

Different stages of spam detection by Google. Source: google

We wish to give thanks to the writer of this write-up for this amazing web content

When Google fights spam with MUM and BERT – SEO and engine news – Abundance


Find here our social media profiles as well as the other related pageshttps://www.ai-magazine.com/related-pages/