Google can now write your emails for you
Published 04/11/2015 | 09:00
Gmail's new 'Smart Reply' function uses artificial intelligence software to suggest the best replies to emails.
Email was supposed to make our lives easier, but has instead turned into an enormous time sink, with workers spending hours every day reading and responding to messages.
Gmail, the world’s biggest email service, made the arduous task somewhat easier when Google introduced it in 2004, but emails still take up around 13 hours a week, according to one survey.
Now, Google wants to help fix this. The internet giant has unveiled Smart Reply, software that provides automatic responses to some emails.
While some email replies clearly need a level of care and attention that only a human can (at this stage) provide, many of them only need a simple “I’ll be there” or “I’ll look into it”.
Gmail’s Smart Reply feature does this by harnessing Google’s artificial intelligence software to interpret an email and craft three different responses.
In one example, the question “Do you have any documentation on how to use the new software” offers three replies: “I don’t, sorry”, “I will have to look for it”, and “I’ll send it to you”.
Users can then pick one of these options and send it to the recipient without typing a word, although the messages can also be edited if need be.
Google said the feature would be available on the English language version of its Inbox by Gmail app for Android and iOS later this week, although there’s no word yet on integrating the feature in the web-based version of Gmail.
While the replies may seem simple, a post from Greg Corrado, a senior research scientist at Google, explained how the software applies the machine learning tools that Google is using across many of its services to understand and form natural language sentences.
Smart Reply is built on two artificial “neural networks” - software that in some ways mimics the structure of the human brain - that Google has “trained” to understand natural language.
Rather than having Google engineers craft rules on how to reply to emails, a neural network can “learn” by scanning the contents of thousands of emails.
Smart Reply employs two neural networks: one to interpret the meaning of an incoming email and another to form a reply. “These systems generalise better, and handle completely new inputs more gracefully than brittle, rule-based systems ever could,” Corrado wrote.
He said that early tests of the software had offered sets of responses that were very similar to each other, so Smart Reply had to be calibrated to provide responses with different “semantic intents”.
Google said another quirk was that the software would often suggest “I love you” in its replies since, naturally, the phrase features in a certain number of emails, but that testing had removed this from the consumer release.