The Profiling Machine: Active Generalization over Knowledge
This work addresses knowledge representation and reasoning for AI systems, but it appears incremental as it adapts existing neural methods to a new task.
The paper tackles the problem of generating expectations from sparse inputs by introducing the task of profiling, inspired by social psychology, and evaluates two neural architectures on Wikidata and crowd expectations to analyze captured knowledge.
The human mind is a powerful multifunctional knowledge storage and management system that performs generalization, type inference, anomaly detection, stereotyping, and other tasks. A dynamic KR system that appropriately profiles over sparse inputs to provide complete expectations for unknown facets can help with all these tasks. In this paper, we introduce the task of profiling, inspired by theories and findings in social psychology about the potential of profiles for reasoning and information processing. We describe two generic state-of-the-art neural architectures that can be easily instantiated as profiling machines to generate expectations and applied to any kind of knowledge to fill gaps. We evaluate these methods against Wikidata and crowd expectations, and compare the results to gain insight in the nature of knowledge captured by various profiling methods. We make all code and data available to facilitate future research.