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

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.