Predicting Relevance Scores for Triples from Type-Like Relations using Neural Embedding - The Cabbage Triple Scorer at WSDM Cup 2017

TL;DR

This paper presents a neural embedding-based method for predicting relevance scores of triples from type-like relations, improving ranking accuracy in entity search tasks.

Contribution

It introduces a deep latent semantic model that captures semantic and syntactic relations for triple scoring, achieving top performance in the WSDM Cup 2017 challenge.

Findings

Achieved an accuracy of 0.74 in relevance scoring

Ranked among top performers in the challenge

Improved semantic relation modeling with deep neural embeddings

Abstract

The WSDM Cup 2017 Triple scoring challenge is aimed at calculating and assigning relevance scores for triples from type-like relations. Such scores are a fundamental ingredient for ranking results in entity search. In this paper, we propose a method that uses neural embedding techniques to accurately calculate an entity score for a triple based on its nearest neighbor. We strive to develop a new latent semantic model with a deep structure that captures the semantic and syntactic relations between words. Our method has been ranked among the top performers with accuracy - 0.74, average score difference - 1.74, and average Kendall's Tau - 0.35.