Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domain

Subal Chandra Roy, Md Motaleb Hossen Manik

TL;DR

This paper presents the development of a question-answering system for Bengali using a fine-tuned BERT-Bangla model in a closed domain and demonstrates promising potential for domain-specific Bengali question-answering systems.

Abstract

Question-answering systems for Bengali have seen limited development, particularly in domain-specific applications. Leveraging advancements in natural language processing, this paper explores a fine-tuned BERT-Bangla model to address this gap. It presents the development of a question-answering system for Bengali using a fine-tuned BERT-Bangla model in a closed domain. The dataset was sourced from Khulna University of Engineering \& Technology's (KUET) website and other relevant texts. The system was trained and evaluated with 2500 question-answer pairs generated from curated data. Key metrics, including the Exact Match (EM) score and F1 score, were used for evaluation, achieving scores of 55.26\% and 74.21\%, respectively. The results demonstrate promising potential for domain-specific Bengali question-answering systems. Further refinements are needed to improve performance for more complex queries.

Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domain

TL;DR

This paper presents the development of a question-answering system for Bengali using a fine-tuned BERT-Bangla model in a closed domain and demonstrates promising potential for domain-specific Bengali question-answering systems.

Abstract

Question-answering systems for Bengali have seen limited development, particularly in domain-specific applications. Leveraging advancements in natural language processing, this paper explores a fine-tuned BERT-Bangla model to address this gap. It presents the development of a question-answering system for Bengali using a fine-tuned BERT-Bangla model in a closed domain. The dataset was sourced from Khulna University of Engineering \& Technology's (KUET) website and other relevant texts. The system was trained and evaluated with 2500 question-answer pairs generated from curated data. Key metrics, including the Exact Match (EM) score and F1 score, were used for evaluation, achieving scores of 55.26\% and 74.21\%, respectively. The results demonstrate promising potential for domain-specific Bengali question-answering systems. Further refinements are needed to improve performance for more complex queries.
Paper Structure (13 sections, 3 equations, 7 figures, 1 table)

This paper contains 13 sections, 3 equations, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Data Collection
  5. Dataset Creation
  6. Fine-Tuning BERT-Bangla
  7. Evaluation
  8. Experimental Analysis
  9. Experimental Setup
  10. Quantitative Results
  11. Qualitative Results
  12. Analysis of Results
  13. Conclusion

Figures (7)

  • Figure 1: Workflow diagram or the framework.
  • Figure 2: Sample dataset.
  • Figure 3: Sample questions.
  • Figure 4: BERT architecture.
  • Figure 5: A single encoder layer.
  • ...and 2 more figures