Contextual Augmentation for Entity Linking using Large Language Models
This addresses entity linking for natural language processing applications, with incremental improvements in performance.
The paper tackles the problem of entity linking by proposing a fine-tuned model that jointly integrates entity recognition and disambiguation in a unified framework, leveraging large language models to enrich context, and achieves state-of-the-art performance on out-of-domain datasets.
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.