Neural Networks for Entity Matching: A Survey

TL;DR

This survey reviews how neural networks and deep learning techniques are applied to entity matching, highlighting recent advances, methodologies, and taxonomy in the field.

Contribution

It provides a comprehensive overview of neural network applications in entity matching, categorizing methods and comparing them to traditional approaches.

Findings

Neural networks are increasingly used in entity matching tasks.

Deep learning methods improve accuracy over traditional techniques.

A taxonomy of neural network models for entity matching is proposed.

Abstract

Entity matching is the problem of identifying which records refer to the same real-world entity. It has been actively researched for decades, and a variety of different approaches have been developed. Even today, it remains a challenging problem, and there is still generous room for improvement. In recent years we have seen new methods based upon deep learning techniques for natural language processing emerge. In this survey, we present how neural networks have been used for entity matching. Specifically, we identify which steps of the entity matching process existing work have targeted using neural networks, and provide an overview of the different techniques used at each step. We also discuss contributions from deep learning in entity matching compared to traditional methods, and propose a taxonomy of deep neural networks for entity matching.