pytorch_neural_symbolic_machines icon indicating copy to clipboard operation
pytorch_neural_symbolic_machines copied to clipboard

Published 20 hours ago • verified publisher icon pcyin

How to preprocess

Open Lucianod28 opened this issue 4 years ago • 0 comments

You mention in README.md you "revised the data pre-processing script, and re-processed the WikiTableQuestions dataset." I see the data utility functions in nsm/data_utils.py, but I don't see a preprocessing script or any explanation of how the preprocessing was done. I'm trying to fine-tune TaBERT for a classification task but I don't see here or in the TaBERT repo a description of the input format required by table_bert.dataset or how to achieve that format. Thanks!

Lucianod28 avatar Aug 12 '20 18:08 Lucianod28