Unveiling Hidden Gems: Enhancing Entity Resolution with a Data Perspective

Entity Resolution (ER), a crucial task in data integration and cleaning, identifies records from different sources that refer to the same entity. Despite advances in existing state-of-the-art (SOTA) methods, a significant challenge remains largely unaddressed: the quality of the data used for training these models. This paper shifts the focus from model-centric improvements to data-centric enhancements, identifying two primary data quality issues: (1) low-hardness positive samples and (2) the scarcity of positive samples relative to negative samples. To tackle these challenges, we propose a novel Data Quality Enhancement Framework (DQEF) comprising an adversarial hardness enhancement method and a noise perturbation-based positive sample generation method. DQEF generates informative and hard positive samples, improving the model’s training effectiveness. As a model-agnostic approach, it can seamlessly integrate with mainstream ER models to enhance performance. Experiments on multiple ER models and real-world datasets show that DQEF significantly boosts performance, surpassing current SOTA results.