About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Ledell Wu
- sl:arxiv_num : 1911.03814
- sl:arxiv_published : 2019-11-10T01:01:45Z
- sl:arxiv_summary : 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 linking, based on fine-tuned BERT
architectures. In the first stage, we do retrieval in a dense space defined by
a bi-encoder that independently embeds the mention context and the entity
descriptions. Each candidate is then examined more carefully with a
cross-encoder, that concatenates the mention and entity text. Our approach
achieves a nearly 5 point absolute gain on a recently introduced zero-shot
entity linking benchmark, driven largely by improvements over previous IR-based
candidate retrieval. We also show that it performs well in the non-zero-shot
setting, obtaining the state-of-the-art result on TACKBP-2010.@en
- sl:arxiv_title : Zero-shot Entity Linking with Dense Entity Retrieval@en
- sl:arxiv_updated : 2019-11-10T01:01:45Z
- sl:bookmarkOf : https://arxiv.org/abs/1911.03814
- sl:creationDate : 2020-05-02
- sl:creationTime : 2020-05-02T11:43:47Z