News for hackers. Stuff that matters.

A comment on Rd-TableBench – Accurately evaluating table extraction.

Re:Rd-TableBench – Accurately evaluating table extraction by gregw2 on Tuesday November 05, 2024 @04:38PM (#42055398)
I have realworld bank statements that I have been unable to find any PDF/AI extractor that can do a good job on.

(To summarize, the core challenge appears to be recognizing nested columnar layout formats combined with odd line wrapping within those columns.)

Is there anyone I can submit an example few pages to for consideration in some benchmark?

[ Parent | on HN ]
Re:Rd-TableBench – Accurately evaluating table extraction by adit_a on Tuesday November 05, 2024 @04:54PM (#42055525)
happy to add examples to future iterations of this dataset if you want to send examples!
[ Parent | on HN ]