@inproceedings{obadinma-etal-2022-bringing,
    title = "Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support",
    author = "Obadinma, Stephen  and
      Khan Khattak, Faiza  and
      Wang, Shirley  and
      Sidhom, Tania  and
      Lau, Elaine  and
      Robertson, Sean  and
      Niu, Jingcheng  and
      Au, Winnie  and
      Munim, Alif  and
      K. Bhaskar, Karthik Raja  and
      Wei, Bencheng  and
      Ren, Iris  and
      Muhammad, Waqar  and
      Li, Erin  and
      Ishola, Bukola  and
      Wang, Michael  and
      Tanner, Griffin  and
      Shiah, Yu-Jia  and
      Zhang, Sean X.  and
      Apponsah, Kwesi P.  and
      Patel, Kanishk  and
      Narain, Jaswinder  and
      Pandya, Deval  and
      Zhu, Xiaodan  and
      Rudzicz, Frank  and
      Dolatabadi, Elham",
    editor = "Li, Yunyao  and
      Lazaridou, Angeliki",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.emnlp-industry.44/",
    doi = "10.18653/v1/2022.emnlp-industry.44",
    pages = "440--450",
    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}."
}