Relevance Score of Triplets Using Knowledge Graph Embedding - The Pigweed Triple Scorer at WSDM Cup 2017

TL;DR

This paper presents a novel ensemble approach combining knowledge graph embeddings and text-based models to accurately score the relevance of entity-attribute triplets, improving entity search ranking.

Contribution

It introduces a new ensemble method that integrates deep semantic embeddings with simple text models for triplet relevance scoring.

Findings

Effective combination of knowledge graph embeddings and bag-of-words models.

Improved relevance scoring accuracy demonstrated in WSDM Cup 2017.

Enhanced entity search ranking performance.

Abstract

Collaborative Knowledge Bases such as Freebase and Wikidata mention multiple professions and nationalities for a particular entity. The goal of the WSDM Cup 2017 Triplet Scoring Challenge was to calculate relevance scores between an entity and its professions/nationalities. Such scores are a fundamental ingredient when ranking results in entity search. This paper proposes a novel approach to ensemble an advanced Knowledge Graph Embedding Model with a simple bag-of-words model. The former deals with hidden pragmatics and deep semantics whereas the latter handles text-based retrieval and low-level semantics.