Something you could do if academia was actually serious about #openscience:
SELECT
DOI FROM PUBLISHED_PAPERS
WHERE
EQUIV_MATHEMATICAL_FORM(myEquation);
There's a challenge out there (forget where) that uses attentional neural networks and the arxiv to learn image -> latex code for equations. It's one peice.
-
-
IMO, that's kind of a hack. Transformations can be lossy. There exists machine-readable structured models/processes to publish/consume this stuff. We just need to use Web-centric tools eg https://dokie.li/ , and academics taking responsibility.
#LinkedResearch -
Er, also to correct myself, the actual challenge did. [Latex] -> [PDF] -> [OCR] -> [Check on Latex] using .tex files.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.