Development of Novel Incremental Question Answering System Using Optimised Deep Belief Network

M. Therasa and G. Mathivanan ()
Additional contact information
M. Therasa: School of Computing, Sathyabama Institute of Science and Technology, (Deemed to be University), Chennai 600119, Tamil Nadu, India
G. Mathivanan: School of Computing, Sathyabama Institute of Science and Technology, (Deemed to be University), Chennai 600119, Tamil Nadu, India

Journal of Information & Knowledge Management (JIKM), 2023, vol. 22, issue 01, 1-28

Abstract: Question answering system is a more eminent research area because of its vast usage in recent years, which can be modelled to solve the deep learning-related limitations. More number of research works have been presented in this question answering field, where most of the systems adopt deep learning as the major contribution. Question answering system focusses on satisfying the users in getting relevant answers regarding a certain question in natural language. This paper presents the incremental question answering system using optimised deep learning. The proposed model covers two-step feature extraction, feature dimension reduction, and deep learning-based classification. From the benchmark dataset collected from a public source, the initial process is to extract the features using word-to-vector. Further, Principle Component Analysis (PCA) is adopted for reducing the dimension of the feature vector. These dimension-reduced features are used for incremental question answering systems by the Optimised Deep Neural Network (O-DNN). Here, the testing weight of the DNN is updated by the Modified Deer Hunting Optimisation Algorithm (M-DHOA) for handling the incremental data. Various implementation details in the algorithms produce better results, which shows the superior performance of the proposed method over existing systems.

Keywords: Question answering systems; incremental learning; Principle Component Analysis; Modified Deer Hunting Optimisation Algorithm; Optimised Deep Neural Network (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219649222500629
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:jikmxx:v:22:y:2023:i:01:n:s0219649222500629

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219649222500629

Access Statistics for this article

Journal of Information & Knowledge Management (JIKM) is currently edited by Professor Suliman Hawamdeh

More articles in Journal of Information & Knowledge Management (JIKM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().