KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph

TL;DR

KGSynNet is a new framework that improves entity synonyms discovery by integrating knowledge graphs, domain-specific embeddings, and a fusion gate to handle out-of-vocabulary mentions and long-tail entities.

Contribution

The paper introduces KGSynNet, a novel entity synonyms discovery framework that effectively leverages knowledge graphs and domain-specific embeddings with a fusion gate for comprehensive entity representation.

Findings

Achieves 14.7% improvement in hits@3 over state-of-the-art methods.

Outperforms BERT by 8.3% in online entity linking feedback.

Demonstrates effectiveness in leveraging knowledge graphs for entity synonym discovery.

Abstract

Entity synonyms discovery is crucial for entity-leveraging applications. However, existing studies suffer from several critical issues: (1) the input mentions may be out-of-vocabulary (OOV) and may come from a different semantic space of the entities; (2) the connection between mentions and entities may be hidden and cannot be established by surface matching; and (3) some entities rarely appear due to the long-tail effect. To tackle these challenges, we facilitate knowledge graphs and propose a novel entity synonyms discovery framework, named \emph{KGSynNet}. Specifically, we pre-train subword embeddings for mentions and entities using a large-scale domain-specific corpus while learning the knowledge embeddings of entities via a joint TransC-TransE model. More importantly, to obtain a comprehensive representation of entities, we employ a specifically designed \emph{fusion gate} to adaptively absorb the entities' knowledge information into their semantic features. We conduct extensive experiments to demonstrate the effectiveness of our \emph{KGSynNet} in leveraging the knowledge graph. The experimental results show that the \emph{KGSynNet} improves the state-of-the-art methods by 14.7\% in terms of hits@3 in the offline evaluation and outperforms the BERT model by 8.3\% in the positive feedback rate of an online A/B test on the entity linking module of a question answering system.