Gmail Smart Compose: Real-Time Assisted Writing
Mia Xu Chen, Benjamin N Lee, Gagan Bansal, Yuan Cao, Shuyuan Zhang,, Justin Lu, Jackie Tsay, Yinan Wang, Andrew M. Dai, Zhifeng Chen, Timothy, Sohn, Yonghui Wu

TL;DR
Smart Compose is a real-time, AI-powered email suggestion system integrated into Gmail, utilizing advanced neural language models and infrastructure to assist users in composing emails efficiently.
Contribution
The paper introduces a large-scale neural language model and novel deployment infrastructure for real-time email suggestions in Gmail.
Findings
High-quality suggestion prediction achieved
Effective real-time inference infrastructure developed
System successfully deployed in Gmail
Abstract
In this paper, we present Smart Compose, a novel system for generating interactive, real-time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In the design and deployment of such a large-scale and complicated system, we faced several challenges including model selection, performance evaluation, serving and other practical issues. At the core of Smart Compose is a large-scale neural language model. We leveraged state-of-the-art machine learning techniques for language model training which enabled high-quality suggestion prediction, and constructed novel serving infrastructure for high-throughput and real-time inference. Experimental results show the effectiveness of our proposed system design and deployment approach. This system is currently being served in Gmail.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Speech and dialogue systems · Natural Language Processing Techniques
