Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support
Abstract
Building Agent Assistants that can help improve customer service support requires inputs from industry users and their customers, as well as knowledge about state-of-the-art Natural Language Processing (NLP) technology. We combine expertise from academia and industry to bridge the gap and build task/domain-specific Neural Agent Assistants (NAA) with three high-level components for: (1) Intent Identification, (2) Context Retrieval, and (3) Response Generation. In this paper, we outline the pipeline of the NAA's core system and also present three case studies in which three industry partners successfully adapt the framework to find solutions to their unique challenges. Our findings suggest that a collaborative process is instrumental in spurring the development of emerging NLP models for Conversational AI tasks in industry. The full reference implementation code and results are available at \url{https://github.com/VectorInstitute/NAA}
Keywords
Cite
@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}
}
Comments
Camera Ready Version of Paper Published in EMNLP 2022 Industry Track