Triple Scoring Using a Hybrid Fact Validation Approach - The Catsear Triple Scorer at WSDM Cup 2017

TL;DR

This paper presents a hybrid approach for triple scoring in knowledge bases, combining multiple sources with linear regression to rank triples by relevance, achieving high accuracy and competitive results in a challenge.

Contribution

The paper introduces a novel hybrid fact validation method that combines multiple data sources for triple scoring using linear regression, improving relevance ranking.

Findings

Achieved 79.58% Accuracy2 in triple scoring

Secured 4th place in WSDM Cup 2017

Demonstrated effectiveness of combining sources for relevance ranking

Abstract

With the continuous increase of data daily published in knowledge bases across the Web, one of the main issues is regarding information relevance. In most knowledge bases, a triple (i.e., a statement composed by subject, predicate, and object) can be only true or false. However, triples can be assigned a score to have information sorted by relevance. In this work, we describe the participation of the Catsear team in the Triple Scoring Challenge at the WSDM Cup 2017. The Catsear approach scores triples by combining the answers coming from three different sources using a linear regression classifier. We show how our approach achieved an Accuracy2 value of 79.58% and the overall 4th place.