Semantic Scholar Open Access 2021 92 sitasi

BioM-Transformers: Building Large Biomedical Language Models with BERT, ALBERT and ELECTRA

Sultan Alrowili Vijay K. Shanker

Abstrak

The impact of design choices on the performance of biomedical language models recently has been a subject for investigation. In this paper, we empirically study biomedical domain adaptation with large transformer models using different design choices. We evaluate the performance of our pretrained models against other existing biomedical language models in the literature. Our results show that we achieve state-of-the-art results on several biomedical domain tasks despite using similar or less computational cost compared to other models in the literature. Our findings highlight the significant effect of design choices on improving the performance of biomedical language models.

Topik & Kata Kunci

Penulis (2)

S

Sultan Alrowili

V

Vijay K. Shanker

Format Sitasi

Alrowili, S., Shanker, V.K. (2021). BioM-Transformers: Building Large Biomedical Language Models with BERT, ALBERT and ELECTRA. https://doi.org/10.18653/v1/2021.bionlp-1.24

Akses Cepat

Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Total Sitasi
92×
Sumber Database
Semantic Scholar
DOI
10.18653/v1/2021.bionlp-1.24
Akses
Open Access ✓