Error Detection in a Large-Scale Lexical Taxonomy

TL;DR

This paper presents a novel distance-based method for detecting and repairing errors in large-scale lexical taxonomies, improving knowledge base quality by leveraging concept relations.

Contribution

It introduces a new approach that measures concept relations via instance distances and proposes algorithms for error detection and correction in knowledge bases.

Findings

Effective error detection in large knowledge bases

Improved cleansing efficiency using hash-based distance calculations

Experimental validation shows high accuracy and efficiency

Abstract

Knowledge base (KB) is an important aspect in artificial intelligence. One significant challenge faced by KB construction is that it contains many noises, which prevents its effective usage. Even though some KB cleansing algorithms have been proposed, they focus on the structure of the knowledge graph and neglect the relation between the concepts, which could be helpful to discover wrong relations in KB. Motived by this, we measure the relation of two concepts by the distance between their corresponding instances and detect errors within the intersection of the conflicting concept sets. For efficient and effective knowledge base cleansing, we first apply a distance-based Model to determine the conflicting concept sets using two different methods. Then, we propose and analyze several algorithms on how to detect and repairing the errors based on our model, where we use hash method for an efficient way to calculate distance. Experimental results demonstrate that the proposed approaches could cleanse the knowledge bases efficiently and effectively.