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
- 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)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/D17-1277.pdf
- Code
- dalab/deep-ed + additional community code
- Data
- ACE 2004, AIDA CoNLL-YAGO, AQUAINT, CoNLL