I am using the NLP module within Project Setup station and am using both a segmentation model and a extraction model to extract information from PDFs documents.
This all works, though when i surpass a certain amount of documents the segmentation model will fail to run and it will output an error in the sparematrix.cpp file on line 136. Did this happen to any of you?
I notice that there is a limit to the number of documents that you train. For instance, for me, I use 70 documents in training and about 140 for testing. This ratio of training/testing is not very ideal, though I have no other choice for now. I would like to know why this is happening and if so, if there is a solution to it.