Google Inbox will reply to your emails automatically

The company's Smart Reply feature will read the content of your email before writing back

Google Inbox can now compose replies to your emails so you don't have to take time out to respond.

Smart Reply will read the content of the email and then select three appropriate responses for you to choose from, the search giant has confirmed.

If Google thinks the email requires a more sophisticated reply, it will start the conversation off so you only need to craft part of the email message by suggesting short phrases that you can select to start off the process.

Like many of Google's innovations, Smart Reply learns more about the types of responses you are likely to use the more you use the feature.

Advertisement
Advertisement - Article continues below
Advertisement - Article continues below

For example, if you respond asking for more information about a particular product a representative of a company is pitching you, it won't add that reponse as an option next time that contact emails you, but will instead try and predict the flow of a natural conversation.

Greg Corrado, senior research scientist at Google, explained the benefits of using a machine-learned system over a rules-based system.

"Any engineer's ability to invent 'rules' would be quickly outstripped by the tremendous diversity with which real people communicate." he said. "A machine-learned system, by contrast, implicitly captures diverse situations, writing styles, and tones. These systems generalise better, and handle completely new inputs more gracefully than brittle, rule-based systems ever could."

Smart Reply is built on a pair of recurrent neural networks, with the first used to encode the incoming email and the other to predict what the user what want to say in a response. The first network can process nuances in conversation, identifying similarities between different ways of saying the same thing to make sure it translates the meaning correctly.

The response stage, however, is designed to generate three very different replies, rather than bringing up possible replies that all have the same meaning, but just phrased differently.

To do this, Google developed a learning system for mapping natural language responses with different semantic intents, providing the user with very different responses.

Advertisement - Article continues below

"There's actually a lot going on behind the scenes to make Smart Reply work. Inbox uses machine learning to recognize emails that need responses and to generate the natural language responses on the fly," Blint Mikls, software engineer at Google, said. "And much like how Inbox gets better when you report spam, the responses you choose (or don't choose!) help improve future suggestions."

Featured Resources

What you need to know about migrating to SAP S/4HANA

Factors to assess how and when to begin migration

Download now

Your enterprise cloud solutions guide

Infrastructure designed to meet your company's IT needs for next-generation cloud applications

Download now

Testing for compliance just became easier

How you can use technology to ensure compliance in your organisation

Download now

Best practices for implementing security awareness training

How to develop a security awareness programme that will actually change behaviour

Download now
Advertisement

Most Popular

Visit/policy-legislation/data-governance/354496/brexit-security-talks-under-threat-after-uk-accused-of
data governance

Brexit security talks under threat after UK accused of illegally copying Schengen data

10 Jan 2020
Visit/web-browser/30394/what-is-http-error-503-and-how-do-you-fix-it
web browser

What is HTTP error 503 and how do you fix it?

7 Jan 2020
Visit/policy-legislation/data-protection/354492/currys-pc-world-parent-firm-hit-with-ps500k-fine-over
data protection

Currys PC World parent firm hit with £500k fine over historic data breach

9 Jan 2020
Visit/security/ransomware/354483/travelex-disruption-caused-by-devastating-ransomware-attack
ransomware

Travelex disruption caused by devastating ransomware attack

8 Jan 2020