将前沿技术交付客户：面向客服支持的神经智能体助手框架
计算与语言
2023-02-08 v1
摘要
构建可助力改善客服支持的智能体助手，需要来自行业用户及其客户的输入，以及关于前沿自然语言处理（NLP）技术的知识。我们结合学术界与工业界专长以弥合鸿沟，并构建具有三个高层组件的特定任务/领域神经智能体助手（NAA）：(1)意图识别，(2)上下文检索，与(3)回复生成。本文中，我们概述NAA核心系统的流水线，并呈现三个案例研究，其中三家行业合作伙伴成功适配该框架以解决其独特挑战。我们的发现表明，协作流程对推动工业界对话式AI任务中新兴NLP模型的发展具有重要作用。完整参考实现代码与结果见 \url{https://github.com/VectorInstitute/NAA}。
引用
@article{arxiv.2302.03222,
title = {Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support},
author = {Stephen Obadinma and Faiza Khan Khattak and Shirley Wang and Tania Sidhom and Elaine Lau and Sean Robertson and Jingcheng Niu and Winnie Au and Alif Munim and Karthik Raja K. Bhaskar and Bencheng Wei and Iris Ren and Waqar Muhammad and Erin Li and Bukola Ishola and Michael Wang and Griffin Tanner and Yu-Jia Shiah and Sean X. Zhang and Kwesi P. Apponsah and Kanishk Patel and Jaswinder Narain and Deval Pandya and Xiaodan Zhu and Frank Rudzicz and Elham Dolatabadi},
journal= {arXiv preprint arXiv:2302.03222},
year = {2023}
}
备注
Camera Ready Version of Paper Published in EMNLP 2022 Industry Track