Issue with a PDF having columnar format

kermitt2 / grobid

A machine learning software for extracting information from scholarly documents

https://grobid.readthedocs.io

Apache License 2.0

3.4k stars 444 forks source link

Issue with a PDF having columnar format #663

Open navraj28 opened 3 years ago

navraj28 commented 3 years ago

Hello There, I am using a Journal that has a columnar format like a newspaper. It has 2 columns of data. When I tried this Journal on the online demo Grobid service, the text from the 2 columns was mixed. Thanks & Regards, Naveen

kermitt2 commented 3 years ago

Hi Naveen,

Can you share maybe some PDF examples (by email if non Open Access) so that we can reproduce the case? Thanks.

navraj28 commented 3 years ago

Thanks for the prompt reply! Sent to patrice.lopez@science-miner.com