We show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate entities are retrieved by approximate nearest neighbor search. Unlike prior work, this setup does not rely on an alias table followed by a re-ranker, and is thus the first fully learned entity retrieval model. We show that our dual encoder, trained using only anchor-text links in Wikipedia, outperforms discrete alias table and BM25 baselines, and is competitive with the best comparable results on the standard TACKBP-2010 dataset. In addition, it can retrieve candidates extremely fast, and generalizes well to a new dataset derived from Wikinews. On the modeling side, we demonstrate the dramatic value of an unsupervised negative mining algorithm for this task.
@article{arxiv.1909.10506,
title = {Learning Dense Representations for Entity Retrieval},
author = {Daniel Gillick and Sayali Kulkarni and Larry Lansing and Alessandro Presta and Jason Baldridge and Eugene Ie and Diego Garcia-Olano},
journal= {arXiv preprint arXiv:1909.10506},
year = {2019}
}