Symbolic processing: Issues and opportunties

Symbolic processing is distinguished from other types of computation, e.g. numeric, commercial, or real-time, by the fact that its metadata is both complex and complicated. That is, the data objects manipulated by symbolic programs have descriptions which are not simple and not always predictable. The metadata is complex in the sense that the data objects are multi-faceted, having a variety of attributes and relationships to other objects. Processing this multidimensional data is done in slices, involving just a few types of attributes at a time, so different programs must deal with different projections (or views) of the data. The metadata is complicated in that it is recursive, meaning that the interpretation of a data object requires processing other instances of the same object class, to an unpredictable extent. Thus complexity and complication in metadata translate directly into data management and resource (space and time) management problems in processing.