End-to-end Biomedical Entity Linking with Span-based Dictionary Matching

Shogo Ujiie, Hayate Iso, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki


Abstract
Disease name recognition and normalization is a fundamental process in biomedical text mining. Recently, neural joint learning of both tasks has been proposed to utilize the mutual benefits. While this approach achieves high performance, disease concepts that do not appear in the training dataset cannot be accurately predicted. This study introduces a novel end-to-end approach that combines span representations with dictionary-matching features to address this problem. Our model handles unseen concepts by referring to a dictionary while maintaining the performance of neural network-based models. Experiments using two major datasaets demonstrate that our model achieved competitive results with strong baselines, especially for unseen concepts during training.
Anthology ID:
2021.bionlp-1.18
Volume:
Proceedings of the 20th Workshop on Biomedical Language Processing
Month:
June
Year:
2021
Address:
Online
Venues:
BioNLP | NAACL
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
162–167
Language:
URL:
https://aclanthology.org/2021.bionlp-1.18
DOI:
10.18653/v1/2021.bionlp-1.18
Bibkey:
Cite (ACL):
Shogo Ujiie, Hayate Iso, Shuntaro Yada, Shoko Wakamiya, and Eiji Aramaki. 2021. End-to-end Biomedical Entity Linking with Span-based Dictionary Matching. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 162–167, Online. Association for Computational Linguistics.
Cite (Informal):
End-to-end Biomedical Entity Linking with Span-based Dictionary Matching (Ujiie et al., BioNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.bionlp-1.18.pdf
Data
BC5CDR