Explore Entity Embedding Effectiveness in Entity Retrieval

TL;DR

This paper investigates the use of entity embeddings derived from knowledge graphs to improve ad-hoc entity retrieval, demonstrating significant performance gains and emphasizing the importance of semantic matching features.

Contribution

It introduces an entity embedding-based model for entity retrieval, showing its effectiveness over previous methods and highlighting the role of semantic features.

Findings

Over 5% improvement over state-of-the-art models

Entity semantic match features are particularly effective

Entity embeddings capture rich semantic relations

Abstract

This paper explores entity embedding effectiveness in ad-hoc entity retrieval, which introduces distributed representation of entities into entity retrieval. The knowledge graph contains lots of knowledge and models entity semantic relations with the well-formed structural representation. Entity embedding learns lots of semantic information from the knowledge graph and represents entities with a low-dimensional representation, which provides an opportunity to establish interactions between query related entities and candidate entities for entity retrieval. Our experiments demonstrate the effectiveness of entity embedding based model, which achieves more than 5\% improvement than the previous state-of-the-art learning to rank based entity retrieval model. Our further analysis reveals that the entity semantic match feature effective, especially for the scenario which needs more semantic understanding.