Figure Descriptive Text Extraction using Ontological Representation

TL;DR

This paper introduces a method that uses ontological semantics to extract and classify descriptive text related to figures in scientific articles, improving over traditional word-based methods.

Contribution

It presents a novel approach employing ontological semantics for extracting and classifying figure descriptions, enhancing accuracy over previous word-based techniques.

Findings

Ontological semantics improves classification accuracy.

Conceptual models outperform word-based approaches.

Enhanced extraction of figure-related information.

Abstract

Experimental research publications provide figure form resources including graphs, charts, and any type of images to effectively support and convey methods and results. To describe figures, authors add captions, which are often incomplete, and more descriptions reside in body text. This work presents a method to extract figure descriptive text from the body of scientific articles. We adopted ontological semantics to aid concept recognition of figure-related information, which generates human- and machine-readable knowledge representations from sentences. Our results show that conceptual models bring an improvement in figure descriptive sentence classification over word-based approaches.