Towards Universal Dense Blocking for Entity Resolution

TL;DR

UniBlocker is a domain-independent dense blocking method for entity resolution, pre-trained on general data, that outperforms prior dense methods and rivals sparse blocking techniques without domain-specific tuning.

Contribution

We introduce UniBlocker, a universal dense blocking model pre-trained on general data, enabling effective entity resolution across diverse domains without domain-specific training.

Findings

UniBlocker outperforms previous dense blocking methods.

It is comparable and complementary to state-of-the-art sparse blocking.

UniBlocker demonstrates high adaptability across multiple domains.

Abstract

Blocking is a critical step in entity resolution, and the emergence of neural network-based representation models has led to the development of dense blocking as a promising approach for exploring deep semantics in blocking. However, previous advanced self-supervised dense blocking approaches require domain-specific training on the target domain, which limits the benefits and rapid adaptation of these methods. To address this issue, we propose UniBlocker, a dense blocker that is pre-trained on a domain-independent, easily-obtainable tabular corpus using self-supervised contrastive learning. By conducting domain-independent pre-training, UniBlocker can be adapted to various downstream blocking scenarios without requiring domain-specific fine-tuning. To evaluate the universality of our entity blocker, we also construct a new benchmark covering a wide range of blocking tasks from multiple domains and scenarios. Our experiments show that the proposed UniBlocker, without any domain-specific learning, significantly outperforms previous self- and unsupervised dense blocking methods and is comparable and complementary to the state-of-the-art sparse blocking methods.