Leveraging large language models for efficient representation learning for entity resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Xiaowei, Foua, Bi T., Wang, Xingqiao, Gunasekaran, Vivek, Talburt, John R.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917839354462208
author Xu, Xiaowei
Foua, Bi T.
Wang, Xingqiao
Gunasekaran, Vivek
Talburt, John R.
author_facet Xu, Xiaowei
Foua, Bi T.
Wang, Xingqiao
Gunasekaran, Vivek
Talburt, John R.
contents In this paper, the authors propose TriBERTa, a supervised entity resolution system that utilizes a pre-trained large language model and a triplet loss function to learn representations for entity matching. The system consists of two steps: first, name entity records are fed into a Sentence Bidirectional Encoder Representations from Transformers (SBERT) model to generate vector representations, which are then fine-tuned using contrastive learning based on a triplet loss function. Fine-tuned representations are used as input for entity matching tasks, and the results show that the proposed approach outperforms state-of-the-art representations, including SBERT without fine-tuning and conventional Term Frequency-Inverse Document Frequency (TF-IDF), by a margin of 3 - 19%. Additionally, the representations generated by TriBERTa demonstrated increased robustness, maintaining consistently higher performance across a range of datasets. The authors also discussed the importance of entity resolution in today's data-driven landscape and the challenges that arise when identifying and reconciling duplicate data across different sources. They also described the ER process, which involves several crucial steps, including blocking, entity matching, and clustering.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10629
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging large language models for efficient representation learning for entity resolution
Xu, Xiaowei
Foua, Bi T.
Wang, Xingqiao
Gunasekaran, Vivek
Talburt, John R.
Computation and Language
Artificial Intelligence
In this paper, the authors propose TriBERTa, a supervised entity resolution system that utilizes a pre-trained large language model and a triplet loss function to learn representations for entity matching. The system consists of two steps: first, name entity records are fed into a Sentence Bidirectional Encoder Representations from Transformers (SBERT) model to generate vector representations, which are then fine-tuned using contrastive learning based on a triplet loss function. Fine-tuned representations are used as input for entity matching tasks, and the results show that the proposed approach outperforms state-of-the-art representations, including SBERT without fine-tuning and conventional Term Frequency-Inverse Document Frequency (TF-IDF), by a margin of 3 - 19%. Additionally, the representations generated by TriBERTa demonstrated increased robustness, maintaining consistently higher performance across a range of datasets. The authors also discussed the importance of entity resolution in today's data-driven landscape and the challenges that arise when identifying and reconciling duplicate data across different sources. They also described the ER process, which involves several crucial steps, including blocking, entity matching, and clustering.
title Leveraging large language models for efficient representation learning for entity resolution
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.10629