Explicit Semantic Ranking For Academic Search Via Knowledge Graph Embedding

Abstract

This paper introduces Explicit Semantic Ranking (<b>ESR</b>), a new ranking technique that leverages knowledge graph embedding. Analysis of the query log from our academic search engine, <b>SemanticScholar.org</b>, reveals that a major error source is its inability to understand the meaning of research concepts in queries. To addresses this challenge, <b>ESR</b> represents queries and documents in the entity space and ranks them based on their semantic connections from their knowledge graph embedding. Experiments demonstrate <b>ESR</b>'s ability in improving <b>Semantic Scholar</b>'s online production system, especially on hard queries where word-based ranking fails.