SciBERT-based Semantification of Bioassays in the Open Research Knowledge Graph

TL;DR

This paper introduces a neural network approach using SciBERT to automatically semantify unstructured bioassay descriptions, significantly improving the accuracy over baseline methods in structuring biological assay data.

Contribution

The paper presents a novel neural-network-based method leveraging SciBERT for the semantification of bioassays, advancing automatic structuring of biological data.

Findings

Neural method achieves 72% F1 score.

Outperforms naive frequency-based baseline.

Demonstrates promising results in bioassay semantification.

Abstract

As a novel contribution to the problem of semantifying biological 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 frequency-based baseline approach. Specifically, the neural method attains 72% F1 versus 47% F1 from the frequency-based method.