Classification of PEPPOL / EHF invoices using OpenNLP

[Andreas Røsdal <an...@gmail.com>]

Hello!
I am interested in using OpenNLP to classify PEPPOL and EHF invoices.
The idea is to use the categorizer and machine learning functionality of
OpenNLP
to automatically categorize invoices according to government standard
accounting codes.
Are there any ongoing open source project using OpenNLP in this way?

Regards,
Andreas R.

Re: Classification of PEPPOL / EHF invoices using OpenNLP

[Jeff Zemerick <jz...@apache.org>]

Hi Andreas,

I'm not familiar with the format of those invoices, and I'm not aware of
any projects using OpenNLP for that exact task.

Depending on the structure of the documents, it may be possible to use
OpenNLP's document categorizer [1] to train a model to categorize the
invoices. If you have a link to a sample invoice I can take a look and give
you a better answer.

[1] https://opennlp.apache.org/docs/1.7.2/manual/opennlp.html#tools.doccat

Thanks,
Jeff

On Thu, Mar 17, 2022 at 4:40 PM Andreas Røsdal <an...@gmail.com>
wrote:

> Hello!
> I am interested in using OpenNLP to classify PEPPOL and EHF invoices.
> The idea is to use the categorizer and machine learning functionality of
> OpenNLP
> to automatically categorize invoices according to government standard
> accounting codes.
> Are there any ongoing open source project using OpenNLP in this way?
>
> Regards,
> Andreas R.
>