Implications between attributes can represent knowledge about objects in a specified context. This knowledge representation is especially useful when it is not possible to list all specified objects. Attribute exploration is a tool of formal concept analysis that supports the acquisition of this knowledge. For a specified context this interactive procedure determines a miminal list of valid implications between attributes of this context together with a list of objects which are counterexamples for all implications not valid in the context. This paper describes how the exploration can be modified such that it determines a mimimal set of implications that fills the gap between previously given implications (called background implications) and all valid implications. The list of implications can be simplified further if exceptions are allowed for the implications.
Auch erschienen in: Bock, Hans-Hermann u.a. (Hrsg.): Data analysis and information systems. (Proceedings of the ... annual conference of the Gesellschaft für Klassifikation e.V. ; 19). Berlin u.a. : Springer, 1996. S. 457-469. ISBN 3-540-60774-9