International Conference on Computer and Knowledge Engineering

Home / 14th International Conference on Computer and Knowledge Engineering

Optimizing Question-Answering Framework Through Integration of Text Summarization Model and Third-Generation Generative Pre-Trained Transformer

Authors :

Ervin Gubin Moung¹ Toh Sin Tong² Maisarah Mohd Sufian³ Valentino Liaw⁴ Ali Farzamnia⁵ Farashazillah Yahya⁶

1- Faculty of Computing and Informatics University Malaysia Sabah 2- Faculty of Computing and Informatics University Malaysia Sabah 3- Faculty of Computing and Informatics Universiti Malaysia Sabah 4- Faculty of Computing and Informatics Universiti Malaysia Sabah 5- School of Computing and Engineering University of Huddersfield 6- Faculty of Computing and Informatics Universiti Malaysia Sabah

Keywords :

Natural Language Processing (NLP)،Seq2Seq،Pre-Trained،Question-Answering Frameworks

Abstract :

This research project addresses the growing demand for efficient data access amidst the surge in digital information. Conventional keyword-based search engines face limitations, driving the exploration of advanced natural language processing (NLP) approaches. The study introduces an algorithm that autonomously extracts data from summary reports, utilizing NLP and information retrieval as a question-answering API. Evaluated using Recall-Oriented Understudy for Gisting Evaluation (ROUGE)-1, ROUGE-2, and ROUGE-L scores, PEGASUS achieved the highest average ROUGE score (0.432) with a single sample, while BART attained the highest multi-sample score (0.302) with 1000 samples. The research emphasized optimal hyperparameters in pre-trained models, specifically the impact of batch size on completion time and the relationship between maximum sequence length and ROUGE scores. By addressing limitations in integrating pre-trained models into Seq2Seq frameworks, the study aims to enhance question-answering solutions for more efficient information retrieval. The research contributes valuable insights to guide future developments in this field with improved efficiency and ROUGE scores.