News for hackers. Stuff that matters.

A comment on Battle of document info extraction services: GCP vs. AWS vs. Azure. Parent comment

Re:Battle of document info extraction services: GCP vs. AWS ... by xpasky on Thursday April 22, 2021 @07:36PM (#26909418)
The natural followup question is how to make these tools easily trainable for a specific document type.

(After all, a human can do it, with some basic training. Ergo we should aim at computer being able to do it with equally simple training too. And in practice this doesn't seem like an insurmountable goal.)

[ Parent | on HN ]
Re:Battle of document info extraction services: GCP vs. AWS ... by grayjay on Thursday April 22, 2021 @09:34PM (#26910119)
That's precisely what people do -- they design workflows that leverage AI to handle the forms that it can, and humans to handle the forms that it can't. And constantly retrain the AI based on what the nice humans just labeled. As the AI gets better less needs to go to the humans, but they're always there for the exceptional cases. BTW this isn't theoretical -- this is current best practice.
[ Parent | on HN ]