Google has just launched a new service called Talk to Books and it leverages machine learning. If you type in a full sentence it searches all the sentences in over 100,000 books to find the ones that respond to your input based on semantic meaning.

Ray Kurzweil, Director of Engineering and Rachel Bernstein, Product Manager, Google Research said in a blog post “Talk to Books is an entirely new way to explore books by starting at the sentence level, rather than the author or topic level. Semantris is a word association game powered by machine learning, where you type out words associated with a given prompt. We have also published “Universal Sentence Encoder”, which describes the models used for these examples in more detail. Lastly, we’ve provided a pretrained semantic TensorFlow module for the community to experiment with their own sentence and phrase encoding.”

“With Talk to Books, we provide an entirely new way to explore books. You make a statement or ask a question, and the tool finds sentences in books that respond, with no dependence on keyword matching. In a sense you are talking to the books, getting responses which can help you determine if you’re interested in reading them or not.”

Keep in mind that Talk to Books just launched and it will be refined over time. If you’d like to learn more about about the underlying code or would like to implement this system in your own apps, you can visit the Developers page.


…read more