Abduction in Semantic Space: Towards a Logic of Discovery

Abstract

Diminishing awareness is a consequence of the information explosion: disciplines are becoming increasingly specialized; individuals and groups are becoming ever more insular. This paper considers how awareness can be enhanced via abductive knowledge discovery the goal of which is to produce suggestions which can span disparate islands of knowledge. Knowledge representation is motivated from a cognitive perspective. Words and concepts are represented as vectors in a high dimensional semantic space automatically derived from a text corpus. Information flow computation between vectors is proposed as a means of suggesting potentially interesting implicit associations between concepts. Information flow is applied to computational scientific discovery by attempting to simulate Swanson's Raynaud-fish oil discovery in medical texts. Both automatic and semi-automatic attempts were studied and compared against suggestions computed via semantic association. Even though this work is preliminary and speculative in nature, there is some justification to believe that appropriate suggestions (hypotheses) can be “abduced” from semantic space.