Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support

TL;DR

This paper presents a framework for building neural agent assistants tailored for customer service, integrating intent detection, context retrieval, and response generation, demonstrated through industry case studies.

Contribution

It introduces a modular pipeline for task-specific neural agent assistants, combining academic and industry expertise, with practical case studies and open-source implementation.

Findings

Collaborative development accelerates NLP model adoption in industry

The framework effectively addresses diverse customer service challenges

Open-source code facilitates reproducibility and further research

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}