Proceedings chapter (Published version) (383 Kb) - 
Free accessOther version: https://biocreative.bioinformatics.udel.edu/media/store/files/2021/Track1_pos_17_BC7_submission_159.pdf
Highlights
Chapitre d'actes
unige:162727 
 |
Drug-protein relation extraction using ensemble of transformer-based language models |
|
| Authors | ||
| Published in | Proceedings of the BioCreative VII Challenge Evaluation Workshop. Online - November 8-10, 2021 - . 2021, p. 89-93 | |
| Abstract | Drug-protein interactions have become a crucial component to study potential side effects, discover new uses for existing drugs, to name a few applications. We describe our approach based on transformer-based language models to predict relations between chemical and gene entities in DrugProt corpus. Sliding window is used to detect the relation in a passage for the individual models, and then they are combined using majority vote. Our model achieved 60% of F1-score (88% of recall and 45% of precision) in the track 1: text mining drug and chemical- protein interactions at BioCreative VII. Ensemble of transformer-based language models provides a baseline performance for drug-protein interaction extraction | |
| Keywords | Transformers — Relation extraction — Ensemble — BERT | |
| Identifiers | ISBN: 978-0-578-32368-8 | |
| Full text |
Proceedings chapter (Published version) (383 Kb) - Free access Other version: https://biocreative.bioinformatics.udel.edu/media/store/files/2021/Track1_pos_17_BC7_submission_159.pdf |
|
| Structures | ||
| Research group | DS4DH - Data Science for Digital Health (1035) | |
| Citation (ISO format) | COPARA ZEA, Jenny Linet, TEODORO, Douglas. Drug-protein relation extraction using ensemble of transformer-based language models. In: Proceedings of the BioCreative VII Challenge Evaluation Workshop. Online. [s.l.] : [s.n.], 2021. p. 89-93. https://archive-ouverte.unige.ch/unige:162727 |
49 hits 
12 downloads 
Contact an author
Update