Entity Matching by Pool-Based Active Learning

Abstract

The goal of entity matching is to find the corresponding records representing the same entity from different data sources. At present, in the mainstream methods, rule-based entity matching methods need tremendous domain knowledge. 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 more likely to overfit, so the quality requirements of training samples are very high. In this paper, we present an active learning method for entity matching tasks. This method needs to manually label only a small number of valuable samples, and use these labeled samples to build a model with high quality. This paper proposes hybrid uncertainty as a query strategy to find those valuable samples for labeling, which can minimize the number of labeled training samples and at the same time meet the requirements of entity matching tasks. The proposed method is validated on seven data sets in different fields. The experiments show that the proposed method uses only a small number of labeled samples and achieves better effects compared to current existing approaches.