Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)

<Previous Article In Volume
Next Article In Volume>

Fine-Tuning Pipeline: A Strategic Approach to Multiclass Text Classification

Authors
Veerababu Reddy1, *, N. Veeranjaneyulu2
1Department of CSE, Vignan’s Foundation for Science Technology & Research. Vadlamudi, Guntur, 522213, India
2Department of IT, Vignan’s Foundation for Science Technology & Research. Vadlamudi, 522213, Guntur,, India
*Corresponding author. Email: veerababureddy@gmail.com
Corresponding Author
Veerababu Reddy
Available Online 30 July 2024.
DOI
10.2991/978-94-6463-471-6_90How to use a DOI?
Keywords
Natural Language Processing; Multi class Text Classification; Prompt Engineering; Pipeline; Fine Tuning; F1 score
Abstract

In present days, many industries are incorporating text classification in their ordinary tasks for consistency, scalability, and timeliness it brings in. However, while working with real data there are several obstacles to overcome during conducting the classification modeling. Natural Language Processing (NLP) is the key component in the extraction and analysis of textual data. Multi-Class Text Classification (MCTC) plays a vital role in categorizing textual data into more than two predetermined classes to avoid ambiguity. Most of the issues faced by previous MCTC models are imbalanced datasets, selecting appropriate algorithms, ensuring model generation, and working with high-dimensional data. A model is developed to overcome these challenges by applying Prompt Engineering, NLP pipeline algorithm, and fine-tuning methods along with GPT-3.0 for the existing MCTC model. This model achieved better results with performance metrics of 0.85 F1 score which shows the best accuracy when compared with all other models, including BERT, Bart, and GPT.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
Series
Advances in Computer Science Research
Publication Date
30 July 2024
ISBN
978-94-6463-471-6
ISSN
2352-538X
DOI
10.2991/978-94-6463-471-6_90How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Veerababu Reddy
AU  - N. Veeranjaneyulu
PY  - 2024
DA  - 2024/07/30
TI  - Fine-Tuning Pipeline: A Strategic Approach to Multiclass Text Classification
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 946
EP  - 954
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_90
DO  - 10.2991/978-94-6463-471-6_90
ID  - Reddy2024
ER  -