Published: Mon, April 16, 2018
Industry | By Terrell Bush

Semantic Experiences open new conversations with Google's AI

Semantic Experiences open new conversations with Google's AI

Google Research is giving us a (fun) look at how far natural language processing in artificial intelligence has come. Semantic Experiences now has two different interactive options, one called Talk to Books, the other called Semantris.

Organizations like Facebook, Twitter, and Google are most widely known for their non-physical forms of technology, such as legendary social media platforms that that roughly nine out of every ten United States citizens use, top-notch search engines that draw in more than one trillion queries each year, and the ability to spread news faster than ever before. In fact to demonstrate their progress on the topic, Google has launched what they are calling "Semantic Experiences". Google has released a module on TensorFlow other researchers and developers can use, so the tech giant's work could lead to more AI-powered applications that can understand how we wield words better than their older counterparts can. Scores are given based on how well the provided word relates to the other words already on the screen. The two games can perceive both inverse and neighboring ideas, even seems like "vroom" for bike or "meow" for cat. The big difference between the two is Arcade's time limit versus Blocks' lack of a timer. They said other potential applications incorporate "classification, semantic similarity, semantic clustering, whitelist applications (choosing the correct reaction from numerous options) and semantic search (of which Talk to Books is a case)".

No. 4 Texas Tech thrashes K-State baseball
Ford pitched just two innings, allowing an earned run on one hit with four walks issued and did not factor into the decision. Tech's Erin Edmoundson (13-9) received the loss on Sunday after entering the game in the third for starter Kassidy Scott.

Users can enter phrases or questions, with Google providing some to get people started, including, "What smell brings back great memories?" The blog says that if you provide full accurate sentences, then the engine "searches all the sentences in over 100,000 books to find the ones that respond to your input based on semantic meaning at the sentence level".

Anyone can try the Talk to Books and Semantris demos for free online.

Like this: