Abstract
Concept normalization, the task of linking textual mentions of concepts to concepts in an ontology, is critical for mining and analyzing biomedical texts. We propose a vector-space model for concept normalization, where mentions and concepts are encoded via transformer networks that are trained via a triplet objective with online hard triplet mining. The transformer networks refine existing pre-trained models, and the online triplet mining makes training efficient even with hundreds of thousands of concepts by sampling training triples within each mini-batch. We introduce a variety of strategies for searching with the trained vector-space model, including approaches that incorporate domain-specific synonyms at search time with no model retraining. Across five datasets, our models that are trained only once on their corresponding ontologies are within 3 points of state-of-the-art models that are retrained for each new domain. Our models can also be trained for each domain, achieving new state-of-the-art on multiple datasets.- Anthology ID:
- 2021.bionlp-1.2
- Original:
- 2021.bionlp-1.2v1
- Version 2:
- 2021.bionlp-1.2v2
- Volume:
- Proceedings of the 20th Workshop on Biomedical Language Processing
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- BioNLP
- SIG:
- SIGBIOMED
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11–22
- Language:
- URL:
- https://aclanthology.org/2021.bionlp-1.2
- DOI:
- 10.18653/v1/2021.bionlp-1.2
- Cite (ACL):
- Dongfang Xu and Steven Bethard. 2021. Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 11–22, Online. Association for Computational Linguistics.
- Cite (Informal):
- Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization (Xu & Bethard, BioNLP 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.bionlp-1.2.pdf
- Code
- dongfang91/triplet-search-connorm