Abstract
This paper briefly describes our works for the LitCovid shared task of BioCreative-VII Track 5. It is an ensemble learning-based system that utilized multiple biomedical pre-trained models. In particular, we leveraged seven advanced models for initialization with homogeneous and heterogenous structures through an ensemble bagging manner. To enhance the representation abilities, we further proposed to employ additional biomedical knowledge to facilitate ensemble learning. The experimental results on the LitCovid datasets show the effectiveness of our proposed approach.
Original language | English |
---|---|
Title of host publication | Proceedings of the BioCreative VII Challenge Evaluation Workshop |
ISBN (Electronic) | 9780578323688 |
Publication status | Published - 2 Nov 2021 |
Event | BioCreative VII Challenge Evaluation Workshop - Online Duration: 8 Nov 2021 → 10 Nov 2021 |
Workshop
Workshop | BioCreative VII Challenge Evaluation Workshop |
---|---|
Period | 8/11/21 → 10/11/21 |
Keywords
- COVID-19
- LitCovid
- Pre-trained Model
- Deep Learning
- Multilabel Classification
- Ensemble Learning