A knowledge graph is a structured representation of facts about entities and their relationships, stored in a graph format. In IR, knowledge graphs are used to enrich search results by adding contextual information about entities, such as people, places, or concepts, and the relationships between them.
Knowledge graphs improve IR by enabling systems to understand the meaning behind search queries and documents. For example, a query about "Apple" could be disambiguated using a knowledge graph to determine whether the user is asking about the tech company or the fruit. This additional layer of understanding helps return more relevant results.
Knowledge graphs also support entity-based search, where users can search for specific entities (e.g., people, organizations, products) and explore related information. They are widely used in applications like Google's Knowledge Graph for answering user queries, recommendation systems, and personalized search engines.