The Profiling Machine: Active Generalization over Knowledge

TL;DR

This paper introduces the task of profiling in knowledge systems, proposing neural architectures that generate expectations over knowledge gaps, with evaluations on Wikidata and crowd data to analyze knowledge representation.

Contribution

It presents two neural profiling architectures inspired by social psychology, enabling dynamic generalization over knowledge bases to fill in missing information.

Findings

Neural profiling models effectively predict missing knowledge.

Profiles align with crowd expectations and Wikidata data.

The approach facilitates reasoning and information processing.

Abstract

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.