Serendipitous knowledge discovery on the Web of Wisdom based on searching and explaining interesting relations in knowledge graphs

Abstract

This paper maintains that the Semantic Web is changing into a kind of Web of Wisdom (WoW) where AI-based problem solving, based on symbolic search and sub-symbolic methods, and Information Retrieval (IR) merge: IR is seen as a process for solving information-related problems of the end user with explanations, a form of knowledge discovery. As a case of example, relational search is concerned, i.e., solving problems of the type “How are $X_1\dots X_n$ related to $Y_1\dots Y_m$?”. For example: how is Pablo Picasso related to Barcelona? The idea is to find explainable “interesting” or even serendipitous associations in Knowledge Graphs (KG) and textual web contents. It is argued that domain knowledge-based symbolic methods based of KGs are needed to complement domain-agnostic graph-based methods and Generative AI (GenAI) boosted by Large Language Models (LLM). By using domain specific knowledge, it is possible to find and explain meaningful reliable textual answers, answer quantitative questions, and use data analyses and visualizations for explaining and studying the relations.