Understanding of medico-technical reports

摘要

Medical practice produces much in the form of written text. The under-usage of this medical text for research is largely due to difficulties in processing the information. The objective of the Aristotle project is to build an automatic data system that is capable of producing a semantic representation of the text in a canonical form. Understanding the text requires identifying objects mentioned in the text, their properties, and the links between them. The nature of the syntactic process allows the connection, step-by-step, of two lexical units. This connection is immediately controlled by the Interpreter, which assumes the semantic process and queries a knowledge base. The syntactic–semantic Interpreter processes one sentence at a time. The Assembler module links the meaning of the different sentences and structures into the output’s shape.