A Theory of Interactive Debugging of Knowledge Bases in Monotonic Logics
This addresses the challenge of maintaining logical consistency in KBs for applications like recommender or expert systems, though it is incremental as it builds on existing non-interactive debuggers.
The paper tackles the problem of debugging knowledge bases (KBs) in monotonic logics, which often suffer from errors due to growth and complexity, by proposing interactive debugging methods that involve users to ensure minimal and correct repairs, resulting in complete, sound, and optimal solutions.
A broad variety of knowledge-based applications such as recommender, expert, planning or configuration systems usually operate on the basis of knowledge represented by means of some logical language. Such a logical knowledge base (KB) enables intelligent behavior of such systems by allowing them to automatically reason, answer queries of interest or solve complex real-world problems. Nowadays, where information acquisition comes at low costs and often happens automatically, the applied KBs are continuously growing in terms of size, information content and complexity. These developments foster the emergence of errors in these KBs and thus pose a significant challenge on all people and tools involved in KB evolution, maintenance and application. If some minimal quality criteria such as logical consistency are not met by some KB, it becomes useless for knowledge-based applications. To guarantee the compliance of KBs with given requirements, (non-interactive) KB debuggers have been proposed. These however often cannot localize all potential faults, suggest too large or incorrect modifications of the faulty KB or suffer from poor scalability due to the inherent complexity of the KB debugging problem. As a remedy to these issues, based on a well-founded theoretical basis this work proposes complete, sound and optimal methods for the interactive debugging of KBs that suggest the one (minimally invasive) error correction of the faulty KB that yields a repaired KB with exactly the intended semantics. Users, e.g. domain experts, are involved in the debugging process by answering automatically generated queries whether some given statements must or must not hold in the domain that should be modeled by the problematic KB at hand.