INFORMATION RETRIEVAL FROM MULTI DOMAIN SPECIFIC RESEARCH PROPOSAL USING HIERARCHICAL BASED NEURAL NETWORK CLUSTERING ALGORITHM

Abstract

Research project selection is an essential task for government and private agencies. When a huge number of research proposals are received, it is common to group them along with their similarities in research discipline areas. In this paper, a new framework is proposed to assign the proposal to reviewer and identify the proposal theme automatically. First, a list of multi word terms are extracted automatically from the domain specific corpus of text documents into a hierarchy based on their semantic similarity. Second, the proximity of two vectors can be calculated using measures such as probabilistic correlation. The conditional probability is used to model the probability that a term appear together in a record. Third, a hierarchical-based neural network clustering algorithm is used to get an information retrieval from multi-domain specific research proposal.