Skip to main navigation menu Skip to main content Skip to site footer

Electrotechnical and Computer Engineering

Vol. 40 No. 12 (2025): Proceedings of the Faculty of Technical Sciences

ОПТИМИЗАЦИЈА ЧЕТБОТА КОРИШЋЕЊЕМ ТРАНСФОРМЕР МОДЕЛА

  • Nađa Kanjuh
DOI:
https://doi.org/10.24867/33BE34Kanjuh
Submitted
January 16, 2026
Published
2026-02-18

Abstract

The goal of this thesis is to optimize a conversational chatbot for the insurance domain using natural language processing algorithms and transformer model, specifically the BERT model, to enhance understanding of language and insurance-specific terminology. In the research, the chatbot was trained and tested in comparison with the LSTM model, with experimental results showing that the BERT model performs better due to its ability to understand broader context in user queries. This capability allows the chatbot to interpret complex and contextually rich queries more accurately, which is especially important for providing precise and reliable information in the insurance domain.

References

  1. [1]Ferrer, J. (2024) How transformers work: A detailed exploration of Transformer architecture, DataCamp.
  2. [2]Nyandwi, J. (2023) Ai Research Blog - The Transformer Blueprint: A holistic guide to the transformer neural network architecture, Deep Learning Revision
  3. [3]Horev, R. (2018) Bert explained: State of the art language model for NLP, Medium.
  4. [4]https://paperswithcode.com/dataset/sts-benchmark