用大模型增强上下文，联合完成实体识别与消歧
Contextual Augmentation for Entity Linking using Large Language Models
- 用大模型扩展实体上下文，统一处理识别与消歧
- 在跨域数据集上达到当前最优性能
- 适合需要高精度实体链接的NLP应用
实体链接旨在检测自然语言文本中的实体提及并将其链接到知识图谱。传统方法采用分步流程，分别使用实体识别和消歧模型，计算开销大且效果有限。本文提出一种微调模型，将实体识别与消歧统一在一个框架中。此外，该方法利用大语言模型增强实体提及的上下文信息，显著提升消歧性能。我们在基准数据集上评估了该方法，并与多个基线对比。结果表明，该方法在跨域数据集上达到当前最优表现。
原文摘要 · Abstract (English)
Entity Linking involves detecting and linking entity mentions in natural language texts to a knowledge graph. Traditional methods use a two-step process with separate models for entity recognition and disambiguation, which can be computationally intensive and less effective. We propose a fine-tuned model that jointly integrates entity recognition and disambiguation in a unified framework. Furthermore, our approach leverages large language models to enrich the context of entity mentions, yielding better performance in entity disambiguation. We evaluated our approach on benchmark datasets and compared with several baselines. The evaluation results show that our approach achieves state-of-the-art performance on out-of-domain datasets.
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。