Gmail智能撰写:实时的辅助写作
Gmail Smart Compose: Real-Time Assisted Writing
摘要:
在本文中,我们提出了智能撰写,一个新的系统,用于生成交互式的,实时的【形】建议,在Gmail中,帮助用户在写邮件,减少重复打字。在设计和部署这样一个大规模、复杂的系统时,我们面临着模型选择、性能评估、服务等实际问题。Smart Compose的核心是一个大规模神经语言模型。我们利用最先进的机器学习技术进行语言模型训练,从而实现高质量的建议预测,并为高吞吐量和实时的【形】推理构建了新颖的服务基础设施。实验结果表明,我们提出的系统设计和部署方法的有效性。该系统目前在Gmail中运行。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。