Contextual Augmentation for Entity Linking using Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vollmers, Daniel, Zahera, Hamada M., Moussallem, Diego, Ngomo, Axel-Cyrille Ngonga
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914107495546880
author Vollmers, Daniel
Zahera, Hamada M.
Moussallem, Diego
Ngomo, Axel-Cyrille Ngonga
author_facet Vollmers, Daniel
Zahera, Hamada M.
Moussallem, Diego
Ngomo, Axel-Cyrille Ngonga
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18888
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contextual Augmentation for Entity Linking using Large Language Models
Vollmers, Daniel
Zahera, Hamada M.
Moussallem, Diego
Ngomo, Axel-Cyrille Ngonga
Computation and Language
Artificial Intelligence
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.
title Contextual Augmentation for Entity Linking using Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.18888