de Meer Pardo, Fernando; Lehmann, Claude; Gehrig, Dennis; Nagy, Andrea; Braschler, Martin; Stockinger, Kurt; Hadji Misheva, Branka; Nicoli, Stefano (2025). GraLMatch : matching groups of entities with graphs and language models Open Proceedings: 28th International Conference on Extending Database Technology (EDBT), Barcelona, Spain, 25-28 March 2025, pp. 1-12.
|
Text
paper-10.pdf - Published Version Available under License Creative Commons: Attribution-Noncommercial-No Derivative Works (CC-BY-NC-ND). Download (1MB) | Preview |
In this paper, we present an end-to-end multi-source Entity Matching problem, which we call entity group matching, where the goal is to assign to the same group records originating from multiple data sources but representing the same real-world entity. We focus on the effects of transitively matched records, i.e. the records connected by paths in the graph G = (V,E) whose nodes and edges represent the records and whether they are a match or not. We present a real-world instance of this problem, where the challenge is to match records of companies and financial securities originating from different data providers. We also introduce two new multi-source benchmark datasets that present similar matching challenges as real-world records. A distinctive characteristic of these records is that they are regularly updated following real-world events, but updates are not applied uniformly across data sources. This phenomenon makes the matching of certain groups of records only possible through the use of transitive information. In our experiments, we illustrate how considering transitively matched records is challenging since a limited amount of false positive pairwise match predictions can throw off the group assignment of large quantities of records. Thus, we propose GraLMatch, a method that can partially detect and remove false positive pairwise predictions through graph-based properties. Finally, we showcase how fine-tuning a Transformer-based model (DistilBERT) on a reduced number of labeled samples yields a better final entity group matching than training on more samples and/or incorporating fine-tuning optimizations, illustrating how precision becomes the deciding factor in the entity group matching of large volumes of records.
Item Type: |
Journal Article (Original Article) |
|---|---|
Division/Institute: |
Bern Academy of the Arts Business School > Institute for Applied Data Science & Finance Business School > Institute for Applied Data Science & Finance > Applied Data Science |
Name: |
de Meer Pardo, Fernando; Lehmann, Claude; Gehrig, Dennis; Nagy, Andrea; Braschler, Martin; Stockinger, Kurt; Hadji Misheva, Branka and Nicoli, Stefano |
ISSN: |
2367-2005 |
Language: |
English |
Submitter: |
Branka Hadji Misheva |
Date Deposited: |
20 Aug 2024 14:37 |
Last Modified: |
20 Aug 2024 14:37 |
Related URLs: |
|
ARBOR DOI: |
10.24451/arbor.22168 |
URI: |
https://arbor.bfh.ch/id/eprint/22168 |
Actions (login required)
 |
View Item |