Efficient Model Repository for Entity Resolution: Construction, Search, and Integration

TL;DR

MoRER is a novel approach that builds a model repository for entity resolution, enabling effective reuse across tasks with limited labeling, outperforming some existing methods.

Contribution

Introduces MoRER, a method for constructing a model repository for ER that leverages feature analysis and clustering to improve performance with less labeling effort.

Findings

MoRER achieves comparable or better results than label-limited methods.

It outperforms self-supervised approaches using large pre-trained models.

MoRER performs comparably or better than supervised transformer-based methods.

Abstract

Entity resolution (ER) is a fundamental task in data integration that enables insights from heterogeneous data sources. The primary challenge of ER lies in classifying record pairs as matches or nonmatches, which in multi-source ER (MS-ER) scenarios can become complicated due to data source heterogeneity and scalability issues. Existing methods for MS-ER generally require labeled record pairs, and such methods fail to effectively reuse models across multiple ER tasks. We propose MoRER (Model Repositories for Entity Resolution), a novel method for building a model repository consisting of classification models that solve ER problems. By leveraging feature distribution analysis, MoRER clusters similar ER tasks, thereby enabling the effective initialization of a model repository with a moderate labeling effort. Experimental results on three multi-source datasets demonstrate that MoRER achieves comparable or better results to methods that have label-limited budgets, such as active learning and transfer learning approaches, while outperforming self-supervised approaches that utilize large pre-trained language models. When compared to supervised transformer-based methods, MoRER achieves comparable or better results, depending on the size of the training data set used.