Published November 12, 2023
| Version v1
Conference proceeding
Open
UIUC-BioNLP @ BioCreative VIII BioRED Track
- 1. Informatics Programs, University of Illinois at Urbana-Champaign
- 2. School of Information Sciences, University of Illinois at Urbana-Champaign
Description
Abstract
In this paper, we present a pipeline approach for the BioCreative VIII BioRED (Biomedical Relation Extraction Dataset) Track. Our approach combines fine-tuned PubMedBERT models for named entity recognition (NER), relation extraction (RE), and novelty detection (ND), with an entity linking (EL) approach based on PubTator and BERN2 models. Our end-to-end system achieved competitive results, ranking above the average and the median scores for all submissions.
This article is part of the Proceedings of the BioCreative VIII Challenge and Workshop: Curation and Evaluation in the era of Generative Models.
Files
UIUC-BioNLP @ BioCreative VIII BioRED Track.pdf
Files
(230.3 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:869642b26b40f72d50e6065884f80b9d
|
230.3 kB | Preview Download |
Additional details
Related works
- Is published in
- Conference proceeding: 10.5281/zenodo.10103190 (DOI)