Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_ai 88% Match Research Paper Data engineers,Database administrators,AI researchers,Enterprise IT professionals 1 week ago

Transformer-Gather, Fuzzy-Reconsider: A Scalable Hybrid Framework for Entity Resolution

large-language-models › model-architecture
📄 Abstract

Abstract: Entity resolution plays a significant role in enterprise systems where data integrity must be rigorously maintained. Traditional methods often struggle with handling noisy data or semantic understanding, while modern methods suffer from computational costs or the excessive need for parallel computation. In this study, we introduce a scalable hybrid framework, which is designed to address several important problems, including scalability, noise robustness, and reliable results. We utilized a pre-trained language model to encode each structured data into corresponding semantic embedding vectors. Subsequently, after retrieving a semantically relevant subset of candidates, we apply a syntactic verification stage using fuzzy string matching techniques to refine classification on the unlabeled data. This approach was applied to a real-world entity resolution task, which exposed a linkage between a central user management database and numerous shared hosting server records. Compared to other methods, this approach exhibits an outstanding performance in terms of both processing time and robustness, making it a reliable solution for a server-side product. Crucially, this efficiency does not compromise results, as the system maintains a high retrieval recall of approximately 0.97. The scalability of the framework makes it deployable on standard CPU-based infrastructure, offering a practical and effective solution for enterprise-level data integrity auditing.
Authors (2)
Mohammadreza Sharifi
Danial Ahmadzadeh
Submitted
September 22, 2025
arXiv Category
cs.DB
arXiv PDF

Key Contributions

Introduces a scalable hybrid framework for entity resolution that combines semantic embeddings from pre-trained language models with fuzzy string matching for syntactic verification. This approach addresses scalability, noise robustness, and improves accuracy in enterprise data linkage tasks.

Business Value

Enhances data quality and consistency in enterprise systems, leading to better decision-making, reduced operational costs, and improved customer relationship management. It's particularly valuable for companies with large, disparate datasets.