The reviewed record of science sign in
Pith

arxiv: 2204.06758 · v1 · pith:45QPBUBC · submitted 2022-04-14 · cs.CL · cs.IR

Multi-label topic classification for COVID-19 literature with Bioformer

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:45QPBUBCrecord.jsonopen to challenge →

classification cs.CL cs.IR
keywords bioformerclassificationtopiccovid-19sentencetaskbiobertliterature
0
0 comments X
read the original abstract

We describe Bioformer team's participation in the multi-label topic classification task for COVID-19 literature (track 5 of BioCreative VII). Topic classification is performed using different BERT models (BioBERT, PubMedBERT, and Bioformer). We formulate the topic classification task as a sentence pair classification problem, where the title is the first sentence, and the abstract is the second sentence. Our results show that Bioformer outperforms BioBERT and PubMedBERT in this task. Compared to the baseline results, our best model increased micro, macro, and instance-based F1 score by 8.8%, 15.5%, 7.4%, respectively. Bioformer achieved the highest micro F1 and macro F1 scores in this challenge. In post-challenge experiments, we found that pretraining of Bioformer on COVID-19 articles further improves the performance.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.