Gmail introduces Smart Reply in Inbox

With so many email addresses, quick accessibility and less dependency on actual phone calls, email is sometimes the most preferred method of communication. This can lead to an abundance of email messages that pile up and create a backlog. It can be painful to reply to all of the emails in your backlog, so Gmail is introducing Smart Reply to help remedy the situation. Smart Reply evaluates your email messages and determines if any of them need responses and will generate a reply for you to choose from.

smartreply1

Smart Reply will offer up to three responses based on your emails for those that need a quick reply. For emails that need more input, Gmail will help jump start your message. Smart Reply should be rolling out later this week and isn’t for your standard Gmail app, instead you need to be using Google’s Inbox for this new feature to work. It will also only be available in English.

I’m not too technical, so if you’re interested in the details of how it works, here is the explanation from Greg Corrado, Senior Research Scientist at Google:

How it works

A naive attempt to build a response generation system might depend on hand-crafted rules for common reply scenarios. But in practice, any engineer’s ability to invent “rules” would be quickly outstripped by the tremendous diversity with which real people communicate. A machine-learned system, by contrast, implicitly captures diverse situations, writing styles, and tones. These systems generalize better, and handle completely new inputs more gracefully than brittle, rule-based systems ever could.

Like other sequence-to-sequence models, 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). This vector, which Geoff Hinton calls a “thought vector,” captures the gist of what is being said without getting hung up on diction — for example, the vector for “Are you free tomorrow?” should be similar to the vector for “Does tomorrow work for you?” 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.

One challenge of working with emails is that the inputs and outputs of the model can be hundreds of words long. This is where the particular choice of recurrent neural network type really matters. We used a variant of a “long short-term-memory” network (or LSTM for short), which is particularly good at preserving long-term dependencies, and can home in on the part of the incoming email that is most useful in predicting a response, without being distracted by less relevant sentences before and after.

Of course, there’s another very important factor in working with email, which is privacy. In developing Smart Reply we adhered to the same rigorous user privacy standards we’ve always held — in other words, no humans reading your email. This means researchers have to get machine learning to work on a data set that they themselves cannot read, which is a little like trying to solve a puzzle while blindfolded — but a challenge makes it more interesting!