Team PolyU-CBSNLP at BioCreative-VII LitCovid Track: Ensemble Learning for COVID-19 Multilabel Classification

Jinghang Gu; Xing Wang; Emmanuele Chersoni; Chu-ren Huang

Team PolyU-CBSNLP at BioCreative-VII LitCovid Track: Ensemble Learning for COVID-19 Multilabel Classification

Jinghang Gu, Xing Wang, Emmanuele Chersoni, Chu-ren Huang

Department of Chinese and Bilingual Studies

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

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

More information

Cite this

@inproceedings{d4ee519780bc4a5391e9ef4144e8eae6,

title = "Team PolyU-CBSNLP at BioCreative-VII LitCovid Track: Ensemble Learning for COVID-19 Multilabel Classification",

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.",

keywords = "COVID-19, LitCovid, Pre-trained Model, Deep Learning, Multilabel Classification, Ensemble Learning",

author = "Jinghang Gu and Xing Wang and Emmanuele Chersoni and Chu-ren Huang",

year = "2021",

month = nov,

day = "2",

language = "English",

booktitle = "Proceedings of the BioCreative VII Challenge Evaluation Workshop",

note = "BioCreative VII Challenge Evaluation Workshop ; Conference date: 08-11-2021 Through 10-11-2021",

}

Gu, J, Wang, X, Chersoni, E & Huang, C 2021, Team PolyU-CBSNLP at BioCreative-VII LitCovid Track: Ensemble Learning for COVID-19 Multilabel Classification. in Proceedings of the BioCreative VII Challenge Evaluation Workshop. BioCreative VII Challenge Evaluation Workshop, 8/11/21. <https://biocreative.bioinformatics.udel.edu/media/store/files/2021/TRACK5_pos_16_BC7_submission_211.pdf>

Team PolyU-CBSNLP at BioCreative-VII LitCovid Track: Ensemble Learning for COVID-19 Multilabel Classification. / Gu, Jinghang; Wang, Xing; Chersoni, Emmanuele et al.
Proceedings of the BioCreative VII Challenge Evaluation Workshop. 2021.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Team PolyU-CBSNLP at BioCreative-VII LitCovid Track

T2 - BioCreative VII Challenge Evaluation Workshop

AU - Gu, Jinghang

AU - Wang, Xing

AU - Chersoni, Emmanuele

AU - Huang, Chu-ren

PY - 2021/11/2

Y1 - 2021/11/2

N2 - 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.

AB - 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.

KW - COVID-19

KW - LitCovid

KW - Pre-trained Model

KW - Deep Learning

KW - Multilabel Classification

KW - Ensemble Learning

M3 - Conference article published in proceeding or book

BT - Proceedings of the BioCreative VII Challenge Evaluation Workshop

Y2 - 8 November 2021 through 10 November 2021

ER -

Team PolyU-CBSNLP at BioCreative-VII LitCovid Track: Ensemble Learning for COVID-19 Multilabel Classification

Abstract

Workshop

Keywords

More information

Fingerprint

Cite this