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
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2619–2629
Language:
URL:
https://aclanthology.org/D17-1277
DOI:
10.18653/v1/D17-1277
Bibkey:
Cite (ACL):
Octavian-Eugen Ganea and Thomas Hofmann. 2017. Deep Joint Entity Disambiguation with Local Neural Attention. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2619–2629, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Deep Joint Entity Disambiguation with Local Neural Attention (Ganea & Hofmann, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1277.pdf
Attachment:
 D17-1277.Attachment.pdf
Code
 dalab/deep-ed +  additional community code
Data
ACE 2004AIDA CoNLL-YAGOAQUAINTCoNLL