I am briefly researching the topic "citation extraction".
So far I have found this Open Source implementation:
http://freecite.library.brown.edu/
The page also contains further links to other implementations.
There also exist a number of scientific papers about citation extraction. I
found these within a few minutes doing a simple Google search, so they do
not necessarily represent the latest state of the art.
A Knowledge-based Approach to Citation Extraction
http://iasl.iis.sinica.edu.tw/webpdf/paper-2005-A_Knowledge-based_Approach_t
o_Citation_Extraction.pdf
High accuracy citation extraction and named entity recognition
for a heterogeneous corpus of academic papers
http://web.science.mq.edu.au/~rdale/publications/papers/2007/49.pdf
Would it make sense to add a citation extraction engine to Stanbol?
What do others think? Any suggestions?
Cheers,
Andreas
