Peng Shi

Hey, Thanks for your interests on our work. You can checkout the pull request https://github.com/awslabs/gap-text2sql/pull/6 when it is merged. I think you can run your own database and queries based...

Hey Kevin, Thanks for your question. So the terminal usually will be a cell value: it could be a float/integer or a string. It usually involves some value copy mechanism...

There is a `score` field in the inference output such as `ie_dirs/bart_run_1_true_1-step41000.infer`. This score might be helpful for helping you to identify low-confidence prediction.

Have you checkout the notebook here https://github.com/awslabs/gap-text2sql/blob/main/rat-sql-gap/notebook.ipynb ? If you can provide more details on the implementation of your `my_test.py`, it would be more helpful.

For the generator code, you can checkout https://github.com/awslabs/gap-text2sql/blob/main/relogic/sql-to-text-train.py and https://github.com/awslabs/gap-text2sql/blob/main/relogic/entity-to-text-train.py, which are sql to text generator and table to text generator. Will upload some data samples to help the understanding.

You can get the ON clause by rules based on the structure of the database. For example, the `concert` table has a foreign key that connect to the primary key...

Thanks for your interest on our work. Did you try to follow the instruction to setup the environment? What is the Python version you use? I assume it is 3.6....

Did your try to setup the virtual environment from the command line we provided? Did that work for you?

@acDante Do you fix this problem ? I got exactly same error as you.

I think my test data is in same format with training and dev (with parse and srl info)