Hi,
I am using the following code to extract the section headers/headings from a scientific paper.
for span in document.spans['layout']:
print(span._.heading)
It works on some headers, but most of time it will provide the incorrect headers. For example, it assumed the footnote as the header due to text formatting.
Hi,
I am using the following code to extract the section headers/headings from a scientific paper.
It works on some headers, but most of time it will provide the incorrect headers. For example, it assumed the footnote as the header due to text formatting.