Selina Engelbrechtsmüller,
"Fine-Tuning Large Language Models for Ticket Classi?cation at Doka GmbH"
, 6-2024, Masterarbeit am Institut für Wirtschaftsinformatik - Data and Knowledge Engineering, Betreuung: o.Univ.-Prof. DI Dr.Michael Schrefl, unter Anleitung von Martin Straßer, MSc
Original Titel:
Fine-Tuning Large Language Models for Ticket Classi?cation at Doka GmbH
Sprache des Titels:
Englisch
Original Kurzfassung:
As digitalization progresses, the number of IT applications in companies constantly increases. This leads to an increase in IT problems, which are usually handled by an IT ticket system in large companies. Doka GmbH also uses such a helpdesk to manually forward tickets to the responsible department for processing. This manual process is very time-consuming and costly. Automatic text classi?cation is required to automate this process. In the past, text classi?cation was performed using traditional classi?ers and, later, deep neural networks (DNN). With the advent of the Transformer architecture, Large Language Models (LLM) such as GPT and BERT were developed. GPT is an LLM published by OpenAI, while Google developed BERT. These are very good at understanding general text but often fail to understand domain-speci?c text such as that found in IT tickets. For this reason, ?ne-tuned models of GPT and BERT are created and compared for the ?ve attributes that describe a ticket at Doka GmbH. Fine-tuning involves training the LLM on a speci?c task and adjusting the model parameters to suit that task during training. It turns out that GPT outperforms BERT in terms of accuracy in 4 out of 5 cases. Data augmentation techniques such as EDA (Easier Data Augmentation) and AEDA (An Easier Data Augmentation) are used to achieve better performance with the ?ne-tuned BERT model. These use methods such as random insertion to ensure that additional labeled data can be generated. The research shows that both techniques can improve the performance of the BERT model.
Sprache der Kurzfassung:
Englisch
Erscheinungsmonat:
6
Erscheinungsjahr:
2024
Notiz zum Zitat:
Masterarbeit am Institut für Wirtschaftsinformatik - Data and Knowledge Engineering, Betreuung: o.Univ.-Prof. DI Dr.Michael Schrefl, unter Anleitung von Martin Straßer, MSc
Forschungs-