Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings

Mattia Atzeni, Mikhail Plekhanov, Frederic Dreyer, Nora Kassner, Simone Merello, Louis Martin, Nicola Cancedda


Abstract
Entity linking methods based on dense retrieval are widely adopted in large-scale applications for their efficiency, but they can fall short of generative models, as they are sensitive to the structure of the embedding space. To address this issue, this paper introduces DUCK, an approach to infusing structural information in the space of entity representations, using prior knowledge of entity types. Inspired by duck typing in programming languages, we define the type of an entity based on its relations with other entities in a knowledge graph. Then, porting the concept of box embeddings to spherical polar coordinates, we represent relations as boxes on the hypersphere. We optimize the model to place entities inside the boxes corresponding to their relations, thereby clustering together entities of similar type. Our experiments show that our method sets new state-of-the-art results on standard entity-disambiguation benchmarks. It improves the performance of the model by up to 7.9 F1 points, outperforms other type-aware approaches, and matches the results of generative models with 18 times more parameters.
Anthology ID:
2023.emnlp-main.566
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9129–9146
Language:
URL:
https://aclanthology.org/2023.emnlp-main.566
DOI:
10.18653/v1/2023.emnlp-main.566
Bibkey:
Cite (ACL):
Mattia Atzeni, Mikhail Plekhanov, Frederic Dreyer, Nora Kassner, Simone Merello, Louis Martin, and Nicola Cancedda. 2023. Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9129–9146, Singapore. Association for Computational Linguistics.
Cite (Informal):
Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings (Atzeni et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.566.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.566.mp4