rss
03-15-2016, 11:42 PM
Smart Reply in Desktop Google Inbox
If you're getting a lot of emails and you're tired of writing replies, Google's Inbox service has a feature that suggests 3 short replies. It was first added (http://gmailblog.blogspot.com/2015/11/computer-respond-to-this-email.html) to the Inbox mobile apps and **w it's available in the desktop site (http://gmailblog.blogspot.com/2015/11/computer-respond-to-this-email.html). Apparently, 10% of all the replies on mobile already use Smart Reply.
https://1.bp.blogspot.com/-A-tTXXDkKCY/VuhtMzWxaaI/AAAAAAACKrM/s8W_RjhxqE0W-v_J4P30shORtXiUcJWQQ/s1600/gmail-smart-reply.png
Smart Reply uses machine learning (http://googleresearch.blogspot.com/2015/11/computer-respond-to-this-email.html) 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. }http://feeds.feedburner.com/~r/GoogleOperatingSystem/~4/68QWx3qGZyY
If you're getting a lot of emails and you're tired of writing replies, Google's Inbox service has a feature that suggests 3 short replies. It was first added (http://gmailblog.blogspot.com/2015/11/computer-respond-to-this-email.html) to the Inbox mobile apps and **w it's available in the desktop site (http://gmailblog.blogspot.com/2015/11/computer-respond-to-this-email.html). Apparently, 10% of all the replies on mobile already use Smart Reply.
https://1.bp.blogspot.com/-A-tTXXDkKCY/VuhtMzWxaaI/AAAAAAACKrM/s8W_RjhxqE0W-v_J4P30shORtXiUcJWQQ/s1600/gmail-smart-reply.png
Smart Reply uses machine learning (http://googleresearch.blogspot.com/2015/11/computer-respond-to-this-email.html) 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. }http://feeds.feedburner.com/~r/GoogleOperatingSystem/~4/68QWx3qGZyY