Benchmarking for biomedical natural language processing tasks with a domain specific ALBERT

Naseem, Usman, Dunn, Adam G., Khushi, Matloob and Kim, Jinman (2022) Benchmarking for biomedical natural language processing tasks with a domain specific ALBERT. BMC Bioinformatics, 23 (1). pp. 1-15. ISSN 1471-2105

[img]
Preview
Text
Benchmarking for Biomedical---.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview

Abstract

Abstract: Background: The abundance of biomedical text data coupled with advances in natural language processing (NLP) is resulting in novel biomedical NLP (BioNLP) applications. These NLP applications, or tasks, are reliant on the availability of domain-specific language models (LMs) that are trained on a massive amount of data. Most of the existing domain-specific LMs adopted bidirectional encoder representations from transformers (BERT) architecture which has limitations, and their generalizability is unproven as there is an absence of baseline results among common BioNLP tasks. Results: We present 8 variants of BioALBERT, a domain-specific adaptation of a lite bidirectional encoder representations from transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine-tuned for 6 different tasks across 20 benchmark datasets. Experiments show that a large variant of BioALBERT trained on PubMed outperforms the state-of-the-art on named-entity recognition (+ 11.09% BLURB score improvement), relation extraction (+ 0.80% BLURB score), sentence similarity (+ 1.05% BLURB score), document classification (+ 0.62% F1-score), and question answering (+ 2.83% BLURB score). It represents a new state-of-the-art in 5 out of 6 benchmark BioNLP tasks. Conclusions: The large variant of BioALBERT trained on PubMed achieved a higher BLURB score than previous state-of-the-art models on 5 of the 6 benchmark BioNLP tasks. Depending on the task, 5 different variants of BioALBERT outperformed previous state-of-the-art models on 17 of the 20 benchmark datasets, showing that our model is robust and generalizable in the common BioNLP tasks. We have made BioALBERT freely available which will help the BioNLP community avoid computational cost of training and establish a new set of baselines for future efforts across a broad range of BioNLP tasks.

Item Type: Article
Uncontrolled Keywords: research, Bioinformatics, Biomedical text mining, BioNLP, domain-specific language model
Subjects: Q Science > Q Science (General)
R Medicine > R Medicine (General)
T Technology > T Technology (General)
Divisions: Faculty of Health & Science > Department of Science & Technology
SWORD Depositor: Pub Router
Depositing User: Pub Router
Date Deposited: 28 Apr 2022 10:13
Last Modified: 28 Apr 2022 10:13
URI: http://oars.uos.ac.uk/id/eprint/2467

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year