Gmail Smart Compose: Real-Time Assisted Writing
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingModel SelectionSimilar Papers 제목 키워드 기반
On the Unintended Social Bias of Training Language Generation Models with News Articles
There are concerns that neural language models may preserve some of the stereotypes of the underlying societies that generate the large corpora needed to train these models. For example, gender bias is a significant prob…
ArticlesManagementMemorizationRepresentation Learning+1On the Unintended Social Bias of Training Language Generation Models with Data from Local Media
There are concerns that neural language models may preserve some of the stereotypes of the underlying societies that generate the large corpora needed to train these models. For example, gender bias is a significant prob…
ArticlesManagementMemorizationRepresentation Learning+1Auto-completion for Te Reo Māori
Typing assistance in online environments is a feature that English-speaking users take for granted. Gmail, as an example, is an email provider for over 1.8 billion users worldwide. However, it fails to support lower reso…
Cultural Vocal Bursts Intensity PredictionEfficient Natural Language Response Suggestion for Smart Reply
This paper presents a computationally efficient machine-learned method for natural language response suggestion. Feed-forward neural networks using n-gram embedding features encode messages into vectors which are optimiz…
Smart Reply: Automated Response Suggestion for Email
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 …
ClusteringDiversity