0% Complete
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 Moung
1
Toh Sin Tong
2
Maisarah Mohd Sufian
3
Valentino Liaw
4
Ali Farzamnia
5
Farashazillah Yahya
6
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.
Papers List
List of archived papers
Farsi Text in Scene: A new dataset
Ali Salmasi - Ehsanollah Kabir
YOLOatt-Med: YOLO-Based Attention Mechanism for Medical Image Classification
Fatemeh Naserizadeh - Erfan Akbarnezhad Sany - Parsa Sinichi - Seyyed Abed Hosseini
Deep Learning Feature Extraction for COVID-19 Detection Algorithm using Computerized Tomography Scan
Maisarah Mohd Sufian - Ervin Gubin Moung - Chong Joon Hou - Ali Farzamnia
A Graph-based Feature Selection using Class-Feature Association Map (CFAM)
Motahare Akhavan - Seyed Mohammad Hossein Hasheminejad
Hybrid navigation based on GPS data and SIFT-based place recognition using Biologically-inspired SLAM
Sahar Salimpour Kasebi - Hadi Seyedarabi - Javad Musevi Niya
PowerLinear Activation Functions with application to the first layer of CNNs
Kamyar Nasiri - Kamaledin Ghiasi-Shirazi
Joint mobility-aware offloading and UAV position optimization in Blockchain-enabled 5G
Zeinab Rabbani - Zeinab Movahedi
Real-Time Gender Recognition with a Deep Neural Network
Samad Azimi Abriz - Majid Meghdadi
Dynamic Hand Gesture Recognition with 2DCNN-LSTM and Improved Keyframe Extraction
Narjes Heidari - Javid Norouzi - Mohammad Sadegh Helfroush - Habibollah Danyal
An Adaptive Budget and Deadline-aware Algorithm for Scheduling Workflows Ensemble in IaaS Clouds
Negin Shafinezhad - Hamid Abrishami - Saeid Abrishami
more
Samin Hamayesh - Version 41.3.1