docling-project / docling-project/docling
Feature request: Parsing citations and references in research papers
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Requested feature
Parsing citations and references in research papers.
### Alternatives
We could simply hardcode _all_ the citation ([examples](https://www.overleaf.com/learn/latex/Biblatex_citation_styles)) and bibliography styles ([examples](https://www.overleaf.com/learn/latex/Biblatex_bibliography_styles)) using regex and identify them in the text itself. This can also be expanded to identify author information, publication venue, year of publication etc. However, this might lead to mismatches if the regex has not been defined in detail and has not been tested on a big enough dataset.
### Uses
The feature would be particularly useful in developing tools for the scientific community - eg. mapping paper sections to references, assessing importance of referred papers with respect to the claims cited by them etc.
Example citations in text:
Example bibliography:
Contributor guide
Assessment
This issue has not been assessed yet.