How to use "analyse.sh" and "filter_dataset.py"?

[ml-nic]

Hello together

First of all, thank you for sharing the code of this project. I was able to train the model and make some predictions, but now I want to find the shortcomings of the model, so I want to analyze on which questions/queries the model performs well.

I found the "analyse.sh" script and the "filter_dataset.py". Now I want to ask you what's the purpose of these files and how to use them.

Thank you for your time Kind regards Nicolas

[mommi84]

Thanks @ml-nic and sorry for the delayed reply.

You can use the analyse.sh script to get insights on how predicates and single tokens were translated:

sh analyse.sh <dataset> <NL test set> <SPARQL test set>

The filter_dataset.py script is used to generate smaller training sets. You need to pass some parameters. The json file contains a dictionary with a counter for each resource, is minimum number of occurrences per resource and the last parameter is a switch for requiring a minimum for all/any resources in the query.

python filter_dataset.py --dataset <dataset> --used_resources used_resources.json --minimum <min> --comp <all|any>