Gmail Smart Compose: Real-Time Assisted Writing
This addresses the problem of email writing efficiency for Gmail users, but it is incremental as it builds on existing neural language model techniques.
The paper tackles the problem of reducing repetitive typing in email composition by developing Smart Compose, a system that provides real-time suggestions in Gmail, resulting in a deployed system with high-quality predictions and efficient serving infrastructure.
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.