Figure Descriptive Text Extraction using Ontological Representation
This work addresses incomplete figure captions in research publications, offering a domain-specific solution for better information retrieval.
The paper tackled the problem of extracting figure descriptive text from scientific article bodies by using ontological semantics for concept recognition, resulting in improved classification over word-based approaches.
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.