Peng Shi
Peng Shi
Could not pull request on gitlab due to large file size
Link to commit 9d90f4792c8c88b707093ea53e4cf9f897ef70af
You can refer to the pull request https://github.com/awslabs/gap-text2sql/pull/23 for more details.
Do you have more details on this? including the command you run, the error you get, etc.
I think the inference will be successful after you finish the preprocessing step.
You can use the official evaluation script https://github.com/taoyds/spider to evaluate the outputs. For customized evaluation in the codebase, "predicted_parse_error": true means the model cannot produce sql. both 0 and false...
You can first refer to the https://github.com/Impavidity/relogic/blob/master/relogic/logickit/modules/span_extractors/average_span_extractor.py. I will reorganize the pre-training code later.
You can refer to the pull request https://github.com/awslabs/gap-text2sql/pull/23 for more details.
This is the output when I run `python run.py preprocess experiments/spider-configs/gap-run.jsonnet`. As you can see, it takes 25mins to preprocess on the train set. ![Screen Shot 2021-08-20 at 3 03...
For the column prediction and recovery, here is one data example. ``` {"entities": {"Award": [], "Designer": [], "Publisher": ["'Ravensburger'"]}, "control_code": [], "question": "What are the award and designer for the...