用大模型+三元组损失提升实体匹配效率与鲁棒性
Leveraging large language models for efficient representation learning for entity resolution
- 基于SBERT和三元组损失进行对比学习微调
- 在多个数据集上性能领先基线3%-19%
- 适合需要高精度实体消歧的工业场景
本文提出TriBERTa，一种利用预训练大语言模型与三元组损失函数的监督式实体解析系统。该系统分两步：首先将实体记录输入句向量双向编码器（SBERT）生成向量表示，再通过基于三元组损失的对比学习进行微调；微调后的表示用于实体匹配任务。实验表明，该方法在多个数据集上优于当前最优方法，包括未微调的SBERT和传统的词频-逆文档频率（TF-IDF），性能提升达3%至19%。此外，所生成表示表现出更强的鲁棒性，在不同数据集上均保持较高且稳定的表现。作者还讨论了实体解析在数据驱动环境中的重要性及跨源重复数据识别与合并的挑战，并阐述了实体解析流程的关键步骤：阻塞、实体匹配与聚类。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。