Open Knowledge Enrichment for Long-tail Entities

TL;DR

This paper presents a comprehensive method for enriching knowledge bases by predicting missing properties and inferring facts for long-tail entities using open Web data, leveraging prior knowledge from popular entities.

Contribution

It introduces a full-fledged approach specifically designed for long-tail entities, addressing gaps left by existing methods that focus only on link completion or value filling.

Findings

Demonstrates the approach's effectiveness on synthetic and real-world datasets.

Shows superiority over related methods in enriching long-tail entities.

Validates the feasibility of using open Web data for knowledge enrichment.

Abstract

Knowledge bases (KBs) have gradually become a valuable asset for many AI applications. While many current KBs are quite large, they are widely acknowledged as incomplete, especially lacking facts of long-tail entities, e.g., less famous persons. Existing approaches enrich KBs mainly on completing missing links or filling missing values. However, they only tackle a part of the enrichment problem and lack specific considerations regarding long-tail entities. In this paper, we propose a full-fledged approach to knowledge enrichment, which predicts missing properties and infers true facts of long-tail entities from the open Web. Prior knowledge from popular entities is leveraged to improve every enrichment step. Our experiments on the synthetic and real-world datasets and comparison with related work demonstrate the feasibility and superiority of the approach.