Deep Joint Entity Disambiguation with Local Neural Attention

Octavian-Eugen Ganea, Thomas Hofmann


Abstract
We propose a novel deep learning model for joint document-level entity disambiguation, which leverages learned neural representations. Key components are entity embeddings, a neural attention mechanism over local context windows, and a differentiable joint inference stage for disambiguation. Our approach thereby combines benefits of deep learning with more traditional approaches such as graphical models and probabilistic mention-entity maps. Extensive experiments show that we are able to obtain competitive or state-of-the-art accuracy at moderate computational costs.
Anthology ID:
D17-1277
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2619–2629
URL:
https://www.aclweb.org/anthology/D17-1277
DOI:
10.18653/v1/D17-1277
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D17-1277.pdf
Attachment:
 D17-1277.Attachment.pdf