Transformers and the Representation of Biomedical Background Knowledge

Author:

Wysocki Oskar1,Zhou Zili2,O’Regan Paul3,Ferreira Deborah4,Wysocka Magdalena5,Landers Dónal6,Freitas André7

Affiliation:

1. Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. oskar.wysocki@manchester.ac.uk

2. Department of Computer Science, University of Manchester. zili.zhou@manchester.ac.uk

3. Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. paul.oregan@digitalecmt.com

4. Department of Computer Science, University of Manchester. deborah.ferreira@manchester.ac.uk

5. Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. magdalena.wysocka@digitalecmt.org

6. Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester. donal.landers@delondraoncology.com

7. Idiap Research Institute Martigny, Switzerland. andre.freitas@manchester.ac.uk

Abstract

Abstract Specialized transformers-based models (such as BioBERT and BioMegatron) are adapted for the biomedical domain based on publicly available biomedical corpora. As such, they have the potential to encode large-scale biological knowledge. We investigate the encoding and representation of biological knowledge in these models, and its potential utility to support inference in cancer precision medicine—namely, the interpretation of the clinical significance of genomic alterations. We compare the performance of different transformer baselines; we use probing to determine the consistency of encodings for distinct entities; and we use clustering methods to compare and contrast the internal properties of the embeddings for genes, variants, drugs, and diseases. We show that these models do indeed encode biological knowledge, although some of this is lost in fine-tuning for specific tasks. Finally, we analyze how the models behave with regard to biases and imbalances in the dataset.

Publisher

MIT Press

Subject

Artificial Intelligence,Computer Science Applications,Linguistics and Language,Language and Linguistics

Reference51 articles.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3