Entity Matching by Pool-based Active Learning

TL;DR

This paper introduces ALMatcher, an active learning approach for entity matching that efficiently selects valuable samples for labeling, reducing the need for extensive labeled data and outperforming existing methods across multiple datasets.

Contribution

The paper proposes a hybrid uncertainty query strategy within an active learning framework to improve entity matching with fewer labeled samples.

Findings

ALMatcher achieves better accuracy with fewer labeled samples.

Validated on seven diverse datasets with superior results.

Reduces labeling effort in entity matching tasks.

Abstract

The goal of entity matching is to find the corresponding records representing the same real-world entity from different data sources. At present, in the mainstream methods, rule-based entity matching methods need tremendous domain knowledge. The machine-learning based or deep-learning based entity matching methods need a large number of labeled samples to build the model, which is difficult to achieve in some applications. In addition, learning-based methods are easy to over-fitting, so the quality requirements of training samples are very high. In this paper, we present an active learning method ALMatcher for the entity matching tasks. This method needs to manually label only a small number of valuable samples, and use these samples to build a model with high quality. This paper proposes a hybrid uncertainty as query strategy to find those valuable samples for labeling, which can minimize the number of labeled training samples meanwhile meet the task requirements. The proposed method has been validated on seven data sets in different fields. The experiment shows that ALMatcher uses only a small number of labeled samples and achieves better results compared to existing approaches.