Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models

Meng, Z. , Liu, F., Shareghi, E., Su, Y., Collins, C. and Collier, N. (2022) Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models. In: 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, 22-27 May 2022, pp. 4798-4810.

[img] Text
265929.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial Share Alike.

418kB

Publisher's URL: https://doi.org/10.18653/v1/2022.acl-long.329

Abstract

Knowledge probing is crucial for understanding the knowledge transfer mechanism behind the pre-trained language models (PLMs). Despite the growing progress of probing knowledge for PLMs in the general domain, specialised areas such as the biomedical domain are vastly under-explored. To facilitate this, we release a well-curated biomedical knowledge probing benchmark, MedLAMA, constructed based on the Unified Medical Language System (UMLS) Metathesaurus. We test a wide spectrum of state-of-the-art PLMs and probing approaches on our benchmark, reaching at most 3% of acc@10. While highlighting various sources of domain-specific challenges that amount to this underwhelming performance, we illustrate that the underlying PLMs have a higher potential for probing tasks. To achieve this, we propose Contrastive-Probe, a novel self-supervised contrastive probing approach, that adjusts the underlying PLMs without using any probing data. While Contrastive-Probe pushes the acc@10 to 28%, the performance gap still remains notable. Our human expert evaluation suggests that the probing performance of our Contrastive-Probe is still under-estimated as UMLS still does not include the full spectrum of factual knowledge. We hope MedLAMA and Contrastive-Probe facilitate further developments of more suited probing techniques for this domain. Our code and dataset are publicly available at https://github.com/cambridgeltl/medlama.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Meng, Dr Zaiqiao
Authors: Meng, Z., Liu, F., Shareghi, E., Su, Y., Collins, C., and Collier, N.
College/School:College of Science and Engineering > School of Computing Science
Copyright Holders:Copyright © 2022 Association for Computational Linguistics
First Published:First published in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers): 4798-4810
Publisher Policy:Reproduced under a Creative Commons licence
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record