Word Level Sequence Tagging #122
Description
Hi, Great work and tutorial to train custom KIE models. I have been training this model for ID cards and using iob_tagging_type as 'box_level'. When I read the paper I got to know it does sequence tagging of entities at character level which makes it little bit difficult to predict per box word level predictions. Giving example here:
if there's a company_name: ASTER with bbox, the entity will get tagged with A,S,T,E,R.
Suppose if decoder makes any mistake then the prediction for the company_name can be: ASTE (R did not predicted as the same entity)
What to do in this type of scenarios? How we can customize decoded to predict word level predictions?