docling-project / docling-project/docling

Feature request: Parsing citations and references in research papers

Open
#906 4 comments 0 reactions 2 assignees Claimed by @deutranium View on GitHub
enhancement
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:

Image

Example bibliography:

Image

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.