An Approach for Product Record Linkage Using Cross-Lingual Learning and Large Language Models

Andre Luiz Firmino Alves, Cláudio Baptista, José Itallo Martins Silva Diniz, Francisco Igor de Lima Mendes, Mateus Cunha

2025

Abstract

Organizations increasingly rely on data for the decision-making process. Nevertheless, significant challenges arise from poor data quality, leading to incomplete, inconsistent, and redundant information. As dependency on data grows, it becomes essential to develop techniques that integrate information from various sources while dealing with these challenges in the context of product matching. Our work investigates information retrieval and entity resolution approaches to product matching problems related to short and varied product descriptions in commercial data, such as those found in electronic invoices. Our proposed approach, STEPMatch, employs deep learning models alongside cross-lingual learning techniques, enhancing adaptability in contexts with limited or incomplete data, effectively identifying products accurately and consistently.

Paper Citation

in Harvard Style

Alves A., Baptista C., Diniz J., Mendes F. and Cunha M. (2025). An Approach for Product Record Linkage Using Cross-Lingual Learning and Large Language Models. In Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS; ISBN 978-989-758-749-8, SciTePress, pages 63-74. DOI: 10.5220/0013285000003929

in Bibtex Style

@conference{iceis25,
author={Andre Alves and Cláudio Baptista and José Diniz and Francisco Mendes and Mateus Cunha},
title={An Approach for Product Record Linkage Using Cross-Lingual Learning and Large Language Models},
booktitle={Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS},
year={2025},
pages={63-74},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013285000003929},
isbn={978-989-758-749-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS
TI - An Approach for Product Record Linkage Using Cross-Lingual Learning and Large Language Models
SN - 978-989-758-749-8
AU - Alves A.
AU - Baptista C.
AU - Diniz J.
AU - Mendes F.
AU - Cunha M.
PY - 2025
SP - 63
EP - 74
DO - 10.5220/0013285000003929
PB - SciTePress