arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.08167cs.CLstat.ML
收藏

OCC:智能回复系统,实现高效的应用内通信

OCC: A Smart Reply System for Efficient In-App Communications

Uber AI(优步AI)

Yue Weng, Huaixiu Zheng, Franziska Bell, Gokhan Tur

摘要:

已经为各种消息平台开发了智能回复系统。在本文中,我们介绍了Uber的智能回复系统:一键聊天(OCC),这是Uber应用内聊天系统的关键增强功能。它使司机合作伙伴能够使用智能回复快速响应骑手消息。智能回复是使用机器学习算法根据对话内容动态选择的。我们的系统由两个主要组成部分:意图检测和回复检索,这是非常不同的标准智能回复系统的任务是直接预测的答复。它是专门为具有短消息和非规范消息的移动应用程序而设计的。回复检索利用基于从历史数据导出的聊天消息中的流行度的意图和回复之间的配对。对于意图检测,我们尝试了一组嵌入和分类技术,并且我们选择部署使用无监督分布式嵌入和最近邻分类器的解决方案。它的优点是只需要少量的标记训练数据,开发和部署到生产中的简单性,以及服务期间的快速推理,因此具有高度的可扩展性。与此同时,它使用深度学习架构(如单词级卷积神经网络)进行搜索。总体而言,该系统在意图检测方面达到了76%的高准确率。目前,该系统已部署在英语国家的生产环境中,71%的乘客和司机之间的应用程序内通信采用了智能回复,以加快通信过程。

英文摘要:

Smart reply systems have been developed for various messaging platforms. In this paper, we introduce Uber's smart reply system: one-click-chat (OCC), which is a key enhanced feature on top of the Uber in-app chat system. It enables driver-partners to quickly respond to rider messages using smart replies. The smart replies are dynamically selected according to conversation content using machine learning algorithms. Our system consists of two major components: intent detection and reply retrieval, which are very different from standard smart reply systems where the task is to directly predict a reply. It is designed specifically for mobile applications with short and non-canonical messages. Reply retrieval utilizes pairings between intent and reply based on their popularity in chat messages as derived from historical data. For intent detection, a set of embedding and classification techniques are experimented with, and we choose to deploy a solution using unsupervised distributed embedding and nearest-neighbor classifier. It has the advantage of only requiring a small amount of labeled training data, simplicity in developing and deploying to production, and fast inference during serving and hence highly scalable. At the same time, it performs comparably with deep learning architectures such as word-level convolutional neural network. Overall, the system achieves a high accuracy of 76% on intent detection. Currently, the system is deployed in production for English-speaking countries and 71% of in-app communications between riders and driver-partners adopted the smart replies to speedup the communication process.

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。

↑