Figure Descriptive Text Extraction Using Ontological Representation

Gilchan Park, Julia Taylor Rayz, Line PouchardZenodo 2020 · DOI · OpenAlex

Abstract

Experimental research publications provide figure form re-sources including graphs, charts, and any type of images to effectively support and convey methods and results. To de-scribe 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.
BibTeX
@inproceedings{park2020figure,
  author = {Gilchan Park and Julia Taylor Rayz and Line Pouchard and Julia Rayz and Line C. Pouchard},
  title = {{Figure Descriptive Text Extraction Using Ontological Representation}},
  booktitle = {Zenodo},
  year = {2020},
  doi = {10.5281/zenodo.6983886},
}

Loading related content...

Figure