@inproceedings{xu-bethard-2021-triplet,
title = "Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization",
author = "Xu, Dongfang and
Bethard, Steven",
booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bionlp-1.2",
doi = "10.18653/v1/2021.bionlp-1.2",
pages = "11--22",
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.",
}
Markdown (Informal)
[Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization](https://aclanthology.org/2021.bionlp-1.2) (Xu & Bethard, BioNLP 2021)
ACL