Contrastive Learning with Hard Negative Entities for Entity Set Expansion

TL;DR

This paper introduces a novel contrastive learning approach with hard negative entities for Entity Set Expansion, significantly improving the ability to distinguish similar entities and outperforming previous methods across multiple datasets.

Contribution

It proposes an entity-level masked language model with contrastive learning and a probabilistic framework called ProbExpan for enhanced entity set expansion.

Findings

Outperforms previous state-of-the-art methods on three datasets.

Effectively handles hard negative entities in entity set expansion.

Provides detailed analysis demonstrating the model's robustness.

Abstract

Entity Set Expansion (ESE) is a promising task which aims to expand entities of the target semantic class described by a small seed entity set. Various NLP and IR applications will benefit from ESE due to its ability to discover knowledge. Although previous ESE methods have achieved great progress, most of them still lack the ability to handle hard negative entities (i.e., entities that are difficult to distinguish from the target entities), since two entities may or may not belong to the same semantic class based on different granularity levels we analyze on. To address this challenge, we devise an entity-level masked language model with contrastive learning to refine the representation of entities. In addition, we propose the ProbExpan, a novel probabilistic ESE framework utilizing the entity representation obtained by the aforementioned language model to expand entities. Extensive experiments and detailed analyses on three datasets show that our method outperforms previous state-of-the-art methods.