{"id":170035,"date":"2019-10-25T22:48:21","date_gmt":"2019-10-25T14:48:21","guid":{"rendered":"https:\/\/www.geek.com\/featured\/-1808538\/"},"modified":"2019-10-25T22:48:21","modified_gmt":"2019-10-25T14:48:21","slug":"google-better-understands-conversational-search-queries","status":"publish","type":"post","link":"https:\/\/itteacheritfreelance.hk\/test\/wordpress\/2019\/10\/25\/google-better-understands-conversational-search-queries\/","title":{"rendered":"Google Better Understands Conversational Search Queries"},"content":{"rendered":"
\n\t\t\t\t\t<\/p>\n
Photo Credit: Google<\/div>\n<\/figure>\n

If I had a nickel for every ambiguous Google Search result I receive, I’d be as rich as a bunch of old white men<\/a>.<\/span><\/p>\n

My net worth will suffer, though, from the company’s new system<\/a> for more natural searching.<\/span><\/p>\n

“With the latest advancements from our research team in the science of language understanding\u2014made possible by machine learning\u2014we’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,” VP of Search Pandu Nayak wrote in a blog post.<\/span><\/p>\n

Google<\/a> is using its BERT, its neural network-based technique for natural language processing pre-training, to better recognize the intent behind searches.<\/span><\/p>\n

“While we’ve continued to improve our language understanding capabilities over the years, we sometimes still don’t quite get it right, particularly with complex or conversational queries,” Nayak said.<\/span><\/p>\n

\"\"<\/p>\n

Photo Credit: Google<\/p>\n<\/div>\n

The inquiry “2019 brazil traveler to USA need a visa,” for instance, is obviously about a Brazilian traveling to the U.S.<\/span><\/p>\n

That may not be so obvious, though, to a computer\u2014which previously would not have understood the importance of the word “to” and its relationship to the rest of the phrase.<\/span><\/p>\n

With BERT, however, Search is able to grasp this nuance and provide more relevant information.<\/span><\/p>\n

In another example\u2014”do estheticians stand a lot at work”\u2014BERT comprehends that “stand” is related to the concept of the physical demands of a job, and displays more useful results.<\/span><\/p>\n

\"\"<\/p>\n

Photo Credit: Google<\/p>\n<\/div>\n

Google hopes to eventually apply English-speaking BERT to searches from across the globe<\/a>.<\/span><\/p>\n

“No matter what you’re looking for, or what language you speak, we hope you’re able to let go of some of your keyword-ese [strings of words people think Google will understand] and search in a way that feels natural to you,” Nayak said. “But you’ll still stump Google from time to time. Even with BERT, we don’t always get it right.”<\/span><\/p>\n

Try searching for “what state is south of Nebraska,” and the AI’s best guess is a community called “South Nebraska.”<\/span><\/p>\n

“Language understanding remains an ongoing challenge, and it keeps us motivated to continue to improve Search,” Nayak continued. “We’re always getting better and working to find the meaning in\u2014and most helpful information for\u2014every query you send our way.”<\/span><\/p>\n

More on Geek.com:<\/span><\/i><\/p>\n