![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh7Q0JOWYKzo5qLNILsG_1Dkf3dZFz3QDFTrS2Rah6fO0yMOh8HHE-Pbn8cbwA68gzTEoF5y_cMHxRNfZ8J4FOXCdf8LM_j8Hucn-ci4cmSLa4Phvn7-kHq3cx2K-rY-cUoFy1_BzoxDo3o/s1600/gmail-smart-reply.png)
Smart Reply uses machine learning to figure out if a short reply is appropriate and then predicts likely responses. "The Smart Reply System is built on a pair of recurrent neural networks, one used to encode the incoming email and one to predict possible responses. The encoding network consumes the words of the incoming email one at a time, and produces a vector (a list of numbers). The second network starts from this thought vector and synthesizes a grammatically correct reply one word at a time, like it's typing it out. Amazingly, the detailed operation of each network is entirely learned, just by training the model to predict likely responses."
{ Thanks, Jonah Langlieb. }
No comments:
Post a Comment