Matching Feature Separation Network for Domain Adaptation in Entity Matching

Chenchen Sun, Yang Xu, Derong shen, Tiezheng Nie

Keywords: Entity matching, Deep neural network, Domain adaptation, Matching feature separation network, Data integration

Abstract: Entity matching (EM) determines whether two records from different data sources refer to the same real-world entity. Currently, deep learning (DL) based EM methods have achieved state-of-the-art (SOTA) results. However, applying DL-based EM methods often costs a lot of human efforts to label the data. To address this challenge, we propose a new domain adaptation (DA) framework for EM called Matching Feature Separation Network (MFSN). We implement DA by separating private and common matching features. Briefly, MFSN first uses three encoders to explicitly model the private and common matching features in both the source and target domains. Then, it transfers the knowledge learned from the source common matching features to the target domain. We also propose an enhanced variant called Feature Representation and Separation Enhanced MFSN (MFSN-FRSE). Compared with MFSN, it has superior feature representation and separation capabilities. We evaluate the effectiveness of MFSN and MFSN-FRSE on twelve transferring EM tasks. The results show that our framework is approximately 7% higher in F1 score on average than the previous SOTA methods. Then, we verify the effectiveness of each module in MFSN and MFSN-FRSE by ablation study. Finally, we explore the optimal strategy of each module in MFSN and MFSN-FRSE through detailed tests.

Track: Semantics and Knowledge

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: No

Submission Number: 471