Demand-Weighted Completeness Prediction for a Knowledge Base
This addresses the issue of assessing and improving knowledge base quality for users relying on structured data, though it is incremental as it builds on existing completeness prediction methods.
The paper tackles the problem of estimating knowledge base completeness based on usage patterns, introducing Demand-Weighted Completeness to predict relation distributions for entities and detect gaps, with a neural network model showing good performance.
In this paper we introduce the notion of Demand-Weighted Completeness, allowing estimation of the completeness of a knowledge base with respect to how it is used. Defining an entity by its classes, we employ usage data to predict the distribution over relations for that entity. For example, instances of person in a knowledge base may require a birth date, name and nationality to be considered complete. These predicted relation distributions enable detection of important gaps in the knowledge base, and define the required facts for unseen entities. Such characterisation of the knowledge base can also quantify how usage and completeness change over time. We demonstrate a method to measure Demand-Weighted Completeness, and show that a simple neural network model performs well at this prediction task.