rat-sql
rat-sql copied to clipboard
microsoft
A relation-aware semantic parsing model from English to SQL
When we use the BERT model to preprocess our own queries (already transformed by the spider). We found that the preprocessing cannot crate a new dev.jsonl file. What should we...
Previous related issue https://github.com/microsoft/rat-sql/issues/21 My command line output: ``` DB connections: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 166/166 [00:00
the problem is as follows: WARNING : superfluous {'name': 'EncDec'} Traceback (most recent call last): File "/home/pl/rat-sql-master/run.py", line 109, in main() File "/home/pl/rat-sql-master/run.py", line 73, in main preprocess.main(preprocess_config) File "/home/pl/rat-sql-master/ratsql/commands/preprocess.py",...
Is there any way to find the '**terminal**' value? "inferred_code": "SELECT singer.Name FROM singer WHERE singer.Age = **'terminal**'"
Hello, If I want to test my own queries,what should I do? Thank you very much.
Hi, Can someone share with us its best pre-trained model (the best model_checkpoint) ? Thank you all.
Jsonnet doesn't work on Windows but Jsonnetbin does. That's why this pull request is proposed. (https://github.com/mcovalt/jsonnetbin)
This change should: - Should speed up preprocess step - Reduce the dependencies of the project (no more need for JDK and Stanford CoreNLP server installation) - Stanza is native...
Hey guys, I've downloaded and managed to preprocess and train the model for the problem. Training was done using the GloVe configuration. During training Accuracy and Loss was printed on...
