Does BERT need domain adaptation for clinical negation detection?
AffiliationUniv Arizona, Sch Informat
MetadataShow full item record
PublisherOXFORD UNIV PRESS
CitationChen Lin, Steven Bethard, Dmitriy Dligach, Farig Sadeque, Guergana Savova, Timothy A Miller, Does BERT need domain adaptation for clinical negation detection?, Journal of the American Medical Informatics Association, Volume 27, Issue 4, April 2020, Pages 584–591, https://doi.org/10.1093/jamia/ocaa001
RightsCopyright © The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: email@example.com.
Collection InformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at firstname.lastname@example.org.
AbstractIntroduction: Classifying whether concepts in an unstructured clinical text are negated is an important unsolved task. New domain adaptation and transfer learning methods can potentially address this issue. Objective: We examine neural unsupervised domain adaptation methods, introducing a novel combination of domain adaptation with transformer-based transfer learning methods to improve negation detection. We also want to better understand the interaction between the widely used bidirectional encoder representations from transformers (BERT) system and domain adaptation methods. Materials and Methods: We use 4 clinical text datasets that are annotated with negation status. We evaluate a neural unsupervised domain adaptation algorithm and BERT, a transformer-based model that is pretrained on massive general text datasets. We develop an extension to BERT that uses domain adversarial training, a neural domain adaptation method that adds an objective to the negation task, that the classifier should not be able to distinguish between instances from 2 different domains. Results: The domain adaptation methods we describe show positive results, but, on average, the best performance is obtained by plain BERT (without the extension). We provide evidence that the gains from BERT are likely not additive with the gains from domain adaptation. Discussion: Our results suggest that, at least for the task of clinical negation detection, BERT subsumes domain adaptation, implying that BERT is already learning very general representations of negation phenomena such that fine-tuning even on a specific corpus does not lead to much overfitting. Conclusion: Despite being trained on nonclinical text, the large training sets of models like BERT lead to large gains in performance for the clinical negation detection task.
Note12 month embargo; published online: 11 February 2020
VersionFinal accepted manuscript