GoKnowGraph: A Multilingual Semantic Search System for Government of Kerala System Documents

Abstract

This paper presents the design and construction of GoKnowGraph, a Knowledge Graph (KG) that is customized exclusively for storing and semantically searching for system documents pertaining to the Government of Kerala (GoK). GoKnowGraph empowers the efficient retrieval of relevant government documents in multiple languages, thus augmenting accessibility and information retrieval within this GoK system. Our contributions encompass the development of a meticulously curated ontology, integrating essential information from GoK, and proposing a robust method for constructing and querying the KG. Moreover, our system supports cross-language document search for queries in English and advanced querying options, including attribute-based filters, to ensure precise information retrieval. Comparative assessments against a state-of-the-art system underscore GoKnowGraph’s pronounced superiority in both relevance and accuracy. The meticulous alignment between user queries and the retrieved documents highlights the platform’s capacity to effectively bridge the gap between unstructured data and the facilitation of informed decision-making within the GoK system.