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

Tom Ayoola, Shubhi Tyagi, Joseph Fisher, Christos Christodoulopoulos, Andrea Pierleoni


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.
Anthology ID:
2022.naacl-industry.24
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
Month:
July
Year:
2022
Address:
Hybrid: Seattle, Washington + Online
Editors:
Anastassia Loukina, Rashmi Gangadharaiah, Bonan Min
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
209–220
Language:
URL:
https://aclanthology.org/2022.naacl-industry.24
DOI:
10.18653/v1/2022.naacl-industry.24
Bibkey:
Cite (ACL):
Tom Ayoola, Shubhi Tyagi, Joseph Fisher, Christos Christodoulopoulos, and Andrea Pierleoni. 2022. ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pages 209–220, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
Cite (Informal):
ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking (Ayoola et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-industry.24.pdf
Video:
 https://aclanthology.org/2022.naacl-industry.24.mp4
Code
 amazon-research/ReFinED +  additional community code
Data
ACE 2004AIDA CoNLL-YAGOAQUAINTCoNLLIPM NELWebQSPWebQuestionsSP