Patrice Lopez

Hi @rabia0001 ! 1) First have a look at the returned XML document (`r.content`) to check the `@coord` is present as expected, if yes it means that the problem is...

Hi @Gavinygh Thanks for the interest in Grobid ! 1) Could you test the deployed server with a curl query (or similar) rather than with the console web app? The...

Hi @frankang Thank you for the issue ! The recognition of figure and table zone is indeed one of the two main problems with Grobid currently. I also think that...

@frankang The other main problem for me is that all the models lack training data ! For example there are only 40 training examples for the fulltext model... Each time...

Yes !

Thanks Luca! There are a few examples of HAL cover page in the segmentation model training data (4 or 5). It's not a lot but I would expect that it's...

Hi @bwakkie ! Likely JDK too high: `openjdk 18.0.2` for the version of logger implementation. In any case, you currently need a lower version of the JDK to run Grobid,...

Hi @com3dian and thank you for the kind words on the project ! Yes Grobid always parse figures when using the processFulltextDocument service. The result XML format is designed to...

If you're using python, there are some available command line scripts to transform Grobid TEI into JSON (some information is lost in the process, but it should cover what you...

Hi @majiajun0 ! Yes you can :) Good news, there is no dirty code to touch. You just need: 1) modify the config file to indicate a deep learning architecture...