Natural Language Processing in IT Ticketing Systems. A conceptual framework for Question-and-Answering machines based on GPT-Algorithms

Marcus Becker and Erika Prokop Dayrell de Lima

Research Journal for Applied Management (RJAM), 2023, vol. 4, issue 1, 133-158

Abstract: This research is a feasibility study to design a Natural Language Processing (NLP) system within a Ques-tion-and-Answering (Q&A) environment for internal IT help desk ticketing operations. The proceedings will be used to develop a conversational agent for an IT consultancy company. Tests with few-shot learning algorithms were performed by calibrating two GPT-2 language models. Another benchmark model was tested on the most recent GPT-3 standard. The input data stems from software license release requests of an internal IT help desk. The final model will be a hybrid approach of first guidance by an automated agent and a human expert intervention for more complicated IT problem. The agent will improve itself by constantly evaluating user feedback.

Keywords: Natural Language Processing; Question Answering; GPT-2; GPT-3; Few-shot learning; Natural Language Generation; Conversational Agent Implementation (search for similar items in EconPapers)
JEL-codes: C67 C88 M15 O31 O32 (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/324733/1/RJAM-4-2023-133.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:ismrja:324733

Access Statistics for this article

Research Journal for Applied Management (RJAM) is currently edited by Ingo Böckenholt

More articles in Research Journal for Applied Management (RJAM) from International School of Management (ISM), Dortmund Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().