• DOI:10.18653/v1/2020.emnlp-main.519
Corpus ID: 207853467

Zero-shot Entity Linking with Dense Entity Retrieval

@inproceedings{Wu2020ZeroshotEL,
  title={Zero-shot Entity Linking with Dense Entity Retrieval},
  author={Ledell Yu Wu and F. Petroni and Martin Josifoski and Sebastian Riedel and Luke Zettlemoyer},
  booktitle={EMNLP},
  year={2020}
}

• Ledell Yu Wu, F. Petroni, +2 authors Luke Zettlemoyer
• Published in EMNLP 2020
• Computer Science

We consider the zero-shot entity-linking challenge where each entity is defined by a short textual description, and the model must read these descriptions together with the mention context to make the final linking decisions. In this setting, retrieving entity candidates can be particularly challenging, since many of the common linking cues such as entity alias tables and link popularity are not available. In this paper, we introduce a simple and effective two-stage approach for zero-shot… Expand

View on ACL

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed