Papers › Intermediate Training of BERT for Product Matching

Intermediate Training of BERT for Product Matching

31 Aug 2020DI2KG: International Workshop on Challenges and Experiences from Data Integration to Knowledge Graphs @ VLDB 2020 2020 8archive 2025-07-28

Ralph Peeters, Christian Bizer, Goran Glavas

Transformer-based models like BERT have pushed the state-of the-art for a wide range of tasks in natural language processing. General-purpose pre-training on large corpora allows Transformers to yield good performance even with small amounts of training data for task-specific fine-tuning. In this work, we apply BERT to the task of product matching in e-commerce and show that BERT is much more training data efficient than other state-of-the-art methods. Moreover, we show that we can further boost its effectiveness through an intermediate training step, exploiting large collections of product offers. Our intermediate training leads to strong performance (>90% F1) on new, unseen products without any product-specific fine-tuning. Further fine-tuning yields additional gains, resulting in improvements of up to 12% F1 for small training sets. Adding the masked language modeling objective in the intermediate training step in order to further adapt the language model to the application domain leads to an additional increase of up to 3% F1.

PaperPDFCode

Code

weyoun2211/productbert-intermediate officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity ResolutionLanguage ModelingLanguage ModellingMasked Language Modeling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Resolution WDC Computers-small BERT F1 (%) 96.53 #1 of 6 Archive leaderboard report
Entity Resolution WDC Computers-xlarge BERT F1 (%) 97.37 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections