Graph-Embedding Empowered Entity Retrieval

TL;DR

This paper systematically evaluates how different graph embedding and entity linking methods affect entity retrieval performance, highlighting the importance of combined structural and textual information and comprehensive entity coverage.

Contribution

It provides a comparative analysis of three graph embedding categories and five entity linking methods, revealing their combined impact on retrieval effectiveness.

Findings

Graph embeddings combining structure and textual info perform best.

Both precision and recall in entity linking are crucial for optimal retrieval.

A comprehensive entity graph improves retrieval outcomes.

Abstract

In this research, we investigate methods for entity retrieval using graph embeddings. While various methods have been proposed over the years, most utilize a single graph embedding and entity linking approach. This hinders our understanding of how different graph embedding and entity linking methods impact entity retrieval. To address this gap, we investigate the effects of three different categories of graph embedding techniques and five different entity linking methods. We perform a reranking of entities using the distance between the embeddings of annotated entities and the entities we wish to rerank. We conclude that the selection of both graph embeddings and entity linkers significantly impacts the effectiveness of entity retrieval. For graph embeddings, methods that incorporate both graph structure and textual descriptions of entities are the most effective. For entity linking, both precision and recall concerning concepts are important for optimal retrieval performance. Additionally, it is essential for the graph to encompass as many entities as possible.