ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking

TL;DR

ReFinED is a fast, accurate, and scalable end-to-end entity linking model that leverages fine-grained types and descriptions, capable of zero-shot linking and handling large knowledge bases efficiently.

Contribution

It introduces ReFinED, a novel end-to-end entity linking approach that significantly improves speed and scalability while maintaining state-of-the-art accuracy.

Findings

Over 60x faster than existing methods

Surpasses state-of-the-art F1 scores by 3.7 on standard datasets

Effective for large-scale and zero-shot entity linking

Abstract

We introduce ReFinED, an efficient end-to-end entity linking model which uses fine-grained entity types and entity descriptions to perform linking. The model performs mention detection, fine-grained entity typing, and entity disambiguation for all mentions within a document in a single forward pass, making it more than 60 times faster than competitive existing approaches. ReFinED also surpasses state-of-the-art performance on standard entity linking datasets by an average of 3.7 F1. The model is capable of generalising to large-scale knowledge bases such as Wikidata (which has 15 times more entities than Wikipedia) and of zero-shot entity linking. The combination of speed, accuracy and scale makes ReFinED an effective and cost-efficient system for extracting entities from web-scale datasets, for which the model has been successfully deployed. Our code and pre-trained models are available at https://github.com/alexa/ReFinED