BioLORD: Learning Ontological Representations from Definitions for Biomedical Concepts and their Textual Descriptions

François Remy, Kris Demuynck, Thomas Demeester


Abstract
This work introduces BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts. State-of-the-art methodologies operate by maximizing the similarity in representation of names referring to the same concept, and preventing collapse through contrastive learning. However, because biomedical names are not always self-explanatory, it sometimes results in non-semantic representations. BioLORD overcomes this issue by grounding its concept representations using definitions, as well as short descriptions derived from a multi-relational knowledge graph consisting of biomedical ontologies. Thanks to this grounding, our model produces more semantic concept representations that match more closely the hierarchical structure of ontologies. BioLORD establishes a new state of the art for text similarity on both clinical sentences (MedSTS) and biomedical concepts (MayoSRS).
Anthology ID:
2022.findings-emnlp.104
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1454–1465
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.104
DOI:
10.18653/v1/2022.findings-emnlp.104
Bibkey:
Cite (ACL):
François Remy, Kris Demuynck, and Thomas Demeester. 2022. BioLORD: Learning Ontological Representations from Definitions for Biomedical Concepts and their Textual Descriptions. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1454–1465, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
BioLORD: Learning Ontological Representations from Definitions for Biomedical Concepts and their Textual Descriptions (Remy et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.104.pdf
Dataset:
 2022.findings-emnlp.104.dataset.zip
Software:
 2022.findings-emnlp.104.software.zip
Video:
 https://aclanthology.org/2022.findings-emnlp.104.mp4