An approach based on Open Research Knowledge Graph for Knowledge Acquisition from scientific papers

TL;DR

This paper presents a method leveraging the Open Research Knowledge Graph to facilitate the organization and extraction of key insights from scientific papers, enhancing knowledge acquisition processes.

Contribution

It introduces an approach using ORKG as a computer-assisted tool for organizing research insights, applied to multiple scientific domains and problems.

Findings

Successfully documented epidemiological surveillance systems

Applied approach to food information engineering and other domains

Enhanced organization of scientific knowledge using ORKG

Abstract

A scientific paper can be divided into two major constructs which are Metadata and Full-body text. Metadata provides a brief overview of the paper while the Full-body text contains key-insights that can be valuable to fellow researchers. To retrieve metadata and key-insights from scientific papers, knowledge acquisition is a central activity. It consists of gathering, analyzing and organizing knowledge embedded in scientific papers in such a way that it can be used and reused whenever needed. Given the wealth of scientific literature, manual knowledge acquisition is a cumbersome task. Thus, computer-assisted and (semi-)automatic strategies are generally adopted. Our purpose in this research was two fold: curate Open Research Knowledge Graph (ORKG) with papers related to ontology learning and define an approach using ORKG as a computer-assisted tool to organize key-insights extracted from research papers. This approach was used to document the "epidemiological surveillance systems design and implementation" research problem and to prepare the related work of this paper. It is currently used to document "food information engineering", "Tabular data to Knowledge Graph Matching" and "Question Answering" research problems and "Neuro-symbolic AI" domain.