Intelligent retrieval for biodiversity

Abstract

[Abstract] A knowledge discovery and representation frame to mine contents in systems biology is described. It applies natural language processing to integrate linguistic and domain knowledge in a mathematical model for information management, formalizing the notion of semantic similarity in different degrees. The goal is to provide computational tools to identify, extract and relate not only data but also scientific notions, even if the information available to start the process is not complete. The interpretation basis is the conceptual graph, a formali sm for semantic representation that allows us to express meaning in a form that is logically precise, humanly readable, and computationally tractable. Our work exploit s the automatic generation of these structures from raw texts through graphical and natural language interaction, providing a solid foundation for the treatment of document incompleteness and query vagueness. We avoid recourse to classic ontologies serving as meta languages for the annotation task that frequently prevent the effective reuse of knowledge, unnecessarily overloading the accessing task for inexpert users, which significantly distances us from previous approaches.