Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning

Panuthep Tasawong, Peerat Limkonchotiwat, Potsawee Manakul, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong


Abstract
Entity disambiguation (ED) is crucial in natural language processing (NLP) for tasks such as question-answering and information extraction. A major challenge in ED is handling overshadowed entities—uncommon entities sharing mention surfaces with common entities. The current approach to enhance performance on these entities involves reasoning over facts in a knowledge base (KB), increasing computational overhead during inference. We argue that the ED performance on overshadowed entities can be enhanced during training by addressing shortcut learning, which does not add computational overhead at inference. We propose a simple yet effective debiasing technique to prevent models from shortcut learning during training. Experiments on a range of ED datasets show that our method achieves state-of-the-art performance without compromising inference speed. Our findings suggest a new research direction for improving entity disambiguation via shortcut learning mitigation.
Anthology ID:
2024.emnlp-main.855
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15313–15321
Language:
URL:
https://aclanthology.org/2024.emnlp-main.855
DOI:
Bibkey:
Cite (ACL):
Panuthep Tasawong, Peerat Limkonchotiwat, Potsawee Manakul, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, and Sarana Nutanong. 2024. Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15313–15321, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning (Tasawong et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.855.pdf