Smart Reply: Automated Response Suggestion for Email

TL;DR

This paper introduces Smart Reply, an end-to-end deep learning system that automatically generates diverse email responses, significantly assisting mobile users by providing quick, semantically relevant suggestions at high scale.

Contribution

It presents a novel scalable system for automated email response generation using large-scale deep learning and a new semantic clustering method requiring minimal labeled data.

Findings

Used in Gmail, responsible for 10% of mobile responses

Processes hundreds of millions of messages daily

Achieves high response diversity and scalability

Abstract

In this paper we propose and investigate a novel end-to-end method for automatically generating short email responses, called Smart Reply. It generates semantically diverse suggestions that can be used as complete email responses with just one tap on mobile. The system is currently used in Inbox by Gmail and is responsible for assisting with 10% of all mobile responses. It is designed to work at very high throughput and process hundreds of millions of messages daily. The system exploits state-of-the-art, large-scale deep learning. We describe the architecture of the system as well as the challenges that we faced while building it, like response diversity and scalability. We also introduce a new method for semantic clustering of user-generated content that requires only a modest amount of explicitly labeled data.