ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking
It provides an efficient and accurate system for extracting entities from web-scale datasets, addressing a bottleneck in natural language processing for applications like knowledge base population.
The paper tackles entity linking by introducing ReFinED, an end-to-end model that performs mention detection, typing, and disambiguation in a single pass, achieving over 60 times faster speed and surpassing state-of-the-art performance by an average of 3.7 F1 on standard datasets.
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