Impact of the Characteristics of Multi-source Entity Matching Tasks on the Performance of Active Learning Methods

Entity matching aims at identifying records in different data sources that describe the same real-world entity. Entity matching is the foundational technique for setting RDF links in the context of the Web of Data. By applying active learning methods for training entity matchers, it is possible to reduce the human labeling effort by selecting informative record pairs for labeling. Although active learning has been extensively studied for the two-data source matching case, it was only recently applied for the task of matching records in multi-source settings, such as the Web of Data. A multi-source matching task has certain inherent characteristics which do not apply for two-source matching tasks and which can be exploited by the active learning query strategy to further reduce the labeling effort. In this paper, we propose a set of profiling dimensions which capture these inherent characteristics of multi-source matching tasks and study their impact on the performance of different active learning methods for training entity matchers. To enable our analysis, we develop ALMSERgen, a multi-source matching task generator and curate a continuum of 252 matching tasks along the suggested profiling dimensions. We use the generated as well as five benchmark tasks to compare the performance of three query strategies: a committee-based strategy, a graph-based strategy, and a strategy that exploits grouping signals. Our results show that graph signals are relevant for multisource matching tasks involving a large amount of records describing the same-real world entities with heterogeneous attribute values while using grouping signals is beneficial if there exists a small number of groups of matching tasks sharing the same underlying patterns.