PoWareMatch: a Quality-aware Deep Learning Approach to Improve Human Schema Matching
This work addresses the challenge of generating quality matches in data integration for fields like databases and AI, though it appears incremental by building on existing human and algorithmic methods.
The paper tackles the problem of improving schema matching by analyzing human matching behavior and introducing unbiased matching, then proposes PoWareMatch, a deep learning approach that calibrates human decisions and combines them with algorithmic matching to achieve high-quality matches, outperforming state-of-the-art algorithms as demonstrated in experiments with over 200 human matchers.
Schema matching is a core task of any data integration process. Being investigated in the fields of databases, AI, Semantic Web and data mining for many years, the main challenge remains the ability to generate quality matches among data concepts (e.g., database attributes). In this work, we examine a novel angle on the behavior of humans as matchers, studying match creation as a process. We analyze the dynamics of common evaluation measures (precision, recall, and f-measure), with respect to this angle and highlight the need for unbiased matching to support this analysis. Unbiased matching, a newly defined concept that describes the common assumption that human decisions represent reliable assessments of schemata correspondences, is, however, not an inherent property of human matchers. In what follows, we design PoWareMatch that makes use of a deep learning mechanism to calibrate and filter human matching decisions adhering the quality of a match, which are then combined with algorithmic matching to generate better match results. We provide an empirical evidence, established based on an experiment with more than 200 human matchers over common benchmarks, that PoWareMatch predicts well the benefit of extending the match with an additional correspondence and generates high quality matches. In addition, PoWareMatch outperforms state-of-the-art matching algorithms.