Giters

pcyin / pytorch_neural_symbolic_machines

A PyTorch Implementation of Neural Symbolic Machines by Liang et al. (2018)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to preprocess

Lucianod28 opened this issue · comments

commented

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!