Google Spelling Algorithm and Passages in Ranking

Google keeps improving its search results and tries to provide the best possible relevant answers. It has gone through many changes over the past 22 years. By using advanced AI (Artificial Intelligence), Google understands the search query to return relevant results. BERT update is a recent example to understand the query of the user. Google has announced that BERT is now being used in almost every query to provide quality results. Below are some new advancements Google is making in search ranking through AI.

Spelling Algorithm

Google has announced a new spelling algorithm to improve its ability to understand misspelled words, and one in 10 queries every day is misspelled. The algorithm uses a deep neural net to improve the ability to decipher misspellings significantly. This helps Google to understand the context and return correct results in under 3 milliseconds.

Passages in Ranking

Also, Google has announced that they have made a new development in ranking in which they will index individual passages as well apart from the web pages. Google said, sometimes one sentence can answer your question, so they will understand the relevancy of passages to find the specific information user is looking for. This will improve 7% of search queries across all languages.

Subtopics

Google said they use neural nets to understand subtopics around an interest to deliver the diversity of content. Google showed the example “home exercise equipment” to understand the subtopics like budget equipment and space ideas to show a range of content.

Please let me know in the comment what do you think of these changes by Google.