Neural Locality Sensitive Hashing for Entity Blocking

TL;DR

This paper introduces NLSHBlock, a neural network-based locality-sensitive hashing method that uses pre-trained language models and a novel loss function to improve entity blocking in complex, real-world scenarios.

Contribution

It proposes a neuralization approach for LSH functions using deep neural networks and fine-tuned language models, addressing limitations of traditional LSH in customized similarity metrics.

Findings

NLSHBlock outperforms existing LSH methods on real-world datasets.

The approach improves entity matching performance in semi-supervised settings.

Extensive evaluations demonstrate significant performance gains.

Abstract

Locality-sensitive hashing (LSH) is a fundamental algorithmic technique widely employed in large-scale data processing applications, such as nearest-neighbor search, entity resolution, and clustering. However, its applicability in some real-world scenarios is limited due to the need for careful design of hashing functions that align with specific metrics. Existing LSH-based Entity Blocking solutions primarily rely on generic similarity metrics such as Jaccard similarity, whereas practical use cases often demand complex and customized similarity rules surpassing the capabilities of generic similarity metrics. Consequently, designing LSH functions for these customized similarity rules presents considerable challenges. In this research, we propose a neuralization approach to enhance locality-sensitive hashing by training deep neural networks to serve as hashing functions for complex metrics. We assess the effectiveness of this approach within the context of the entity resolution problem, which frequently involves the use of task-specific metrics in real-world applications. Specifically, we introduce NLSHBlock (Neural-LSH Block), a novel blocking methodology that leverages pre-trained language models, fine-tuned with a novel LSH-based loss function. Through extensive evaluations conducted on a diverse range of real-world datasets, we demonstrate the superiority of NLSHBlock over existing methods, exhibiting significant performance improvements. Furthermore, we showcase the efficacy of NLSHBlock in enhancing the performance of the entity matching phase, particularly within the semi-supervised setting.