A semantic network or net is a graphic notation for representing knowledge in patterns of interconnected nodes and arcs. Computer implementations of semantic networks were first developed for artificial intelligence and machine translation, but earlier versions have long been used in philosophy, psychology, and linguistics. What is common to all semantic networks is a declarative graphic representation that can be used either to represent knowledge or to support automated systems for reasoning about knowledge. Some versions are highly informal, but other versions are formally defined systems of logic. Following are six of the most common kinds of semantic networks, each of which is discussed in detail in one section of this article. 1. Definitional networks emphasize the subtype or is-a relation between a concept type and a newly defined subtype. The resulting network, also called a generalization or subsumption hierarchy, supports the rule of inheritance for copying properties defined for a supertype to all of its subtypes. Since definitions are true by definition, the information in these networks is often assumed to be necessarily true.

We present a neural network based approach to the extraction of information from a medical database. Medical concepts are encoded by using conceptual graphs, which have been demonstrated useful for this purpose. The medical conceptual graphs are encoded into a paticular neural network architecture, i.e., the Labeling RAAM, which allows the processing of structures both using pointers (reduced descriptors) and by content. Associative queries to the database are implemented by Generalized Hopfield Networks, which are generated `on the fly' by opportunely composing the weights of the LRAAM. Complex concepts are retrieved starting from basic or partial concepts conveyed by medical sentences.

The meaning of medical texts... In this paper we discuss the possibility to memorize and retrieve natural language sentences and especially medical language sentences given in this kind of formalism with the use of the LRAAM model [Spe93b, Spe93a]. In Section 2 we explain the idea underlying conceptual graphs. In Section 3 we briefly expose the access by content capabilities of the LRAAM and suggest a generalization of the access by content procedures introducing the concept of Generalized Hopfield Network. A discussion on the impact of this generalization on knowledge extraction from a database of conceptual graphs is given in the conclusion.