SciBERT-based semantification of bioassays in the open research knowledge graph

Marco Anteghini, Jennifer D'Souza, Vitor A.P. Martins Dos Santos, Sören Auer

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

Abstract

As a novel contribution to the problem of semantifying bio- logical assays, in this paper, we propose a neural-network-based approach to automatically semantify, thereby structure, unstructured bioassay text descriptions. Experimental evaluations, to this end, show promise as the neural-based semantification significantly outperforms a naive frequencybased baseline approach. Specifically, the neural method attains 72% F1 versus 47% F1 from the frequency-based method. The work in this paper aligns with the present cutting-edge trend of the scholarly knowledge digitalization impetus which aim to convert the long-standing document-based format of scholarly content into knowledge graphs (KG). To this end, our selected data domain of bioassays are a prime candidate for structuring into KGs.

Original languageEnglish
Title of host publicationEKAW-PD 2020
Subtitle of host publicationPosters and Demonstrations at EKAW 2020
EditorsD. Garijo, A. Lawrynowicz
PublisherRheinisch-Westfaelische Technische Hochschule Aachen
Pages22-30
Number of pages9
Volume2751
Publication statusPublished - 17 Sep 2020
Event22nd International Conference on Knowledge Engineering and Knowledge Management - Posters and Demonstrations Session, EKAW-PD 2020 - Virtual, Bozen-Bolzano, Italy
Duration: 16 Sep 202018 Sep 2020

Publication series

NameCEUR Workshop Proceedings
PublisherRheinisch-Westfaelische Technische Hochschule Aachen
ISSN (Print)1613-0073

Conference

Conference22nd International Conference on Knowledge Engineering and Knowledge Management - Posters and Demonstrations Session, EKAW-PD 2020
CountryItaly
CityVirtual, Bozen-Bolzano
Period16/09/2018/09/20

Keywords

  • Bioassays
  • Machine Learning
  • Open Science Graphs

Fingerprint Dive into the research topics of 'SciBERT-based semantification of bioassays in the open research knowledge graph'. Together they form a unique fingerprint.

Cite this