BERT-based similarity learning for product matching

Janusz Tracz, Piotr Iwo Wójcik, Kalina Jasinska-Kobus, Riccardo Belluzzo, Robert Mroczkowski, Ireneusz Gawlik


Abstract
Product matching, i.e., being able to infer the product being sold for a merchant-created offer, is crucial for any e-commerce marketplace, enabling product-based navigation, price comparisons, product reviews, etc. This problem proves a challenging task, mostly due to the extent of product catalog, data heterogeneity, missing product representants, and varying levels of data quality. Moreover, new products are being introduced every day, making it difficult to cast the problem as a classification task. In this work, we apply BERT-based models in a similarity learning setup to solve the product matching problem. We provide a thorough ablation study, showing the impact of architecture and training objective choices. Application of transformer-based architectures and proper sampling techniques significantly boosts performance for a range of e-commerce domains, allowing for production deployment.
Anthology ID:
2020.ecomnlp-1.7
Volume:
Proceedings of Workshop on Natural Language Processing in E-Commerce
Month:
Dec
Year:
2020
Address:
Barcelona, Spain
Venue:
EcomNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
66–75
Language:
URL:
https://aclanthology.org/2020.ecomnlp-1.7
DOI:
Bibkey:
Cite (ACL):
Janusz Tracz, Piotr Iwo Wójcik, Kalina Jasinska-Kobus, Riccardo Belluzzo, Robert Mroczkowski, and Ireneusz Gawlik. 2020. BERT-based similarity learning for product matching. In Proceedings of Workshop on Natural Language Processing in E-Commerce, pages 66–75, Barcelona, Spain. Association for Computational Linguistics.
Cite (Informal):
BERT-based similarity learning for product matching (Tracz et al., EcomNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.ecomnlp-1.7.pdf