Update README.md
Browse files
README.md
CHANGED
|
@@ -3,11 +3,15 @@ datasets:
|
|
| 3 |
- spider
|
| 4 |
language:
|
| 5 |
- en
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# T5 large LM Adapt for Text to SQL
|
| 9 |
|
| 10 |
-
This model is fine-tuned from the [t5-large-LM-adapt](https://huggingface.co/google/t5-large-lm-adapt) checkpoint.
|
|
|
|
| 11 |
|
| 12 |
## Spider and Spider-Syn dataset
|
| 13 |
|
|
|
|
| 3 |
- spider
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
+
pipeline_tag: text2text-generation
|
| 7 |
+
tags:
|
| 8 |
+
- text2sql
|
| 9 |
---
|
| 10 |
|
| 11 |
# T5 large LM Adapt for Text to SQL
|
| 12 |
|
| 13 |
+
This model is fine-tuned from the [t5-large-LM-adapt](https://huggingface.co/google/t5-large-lm-adapt) checkpoint.
|
| 14 |
+
While training the model on text 2 SQL task, the model learns how to generate a SQL query based on the question posed in natural language, however in some cases the SQL query contains unknown column etc. and alltogether does not take the schema of the specific database into account. That is where our approach come in. We incorporated the database schema into the input question, to specify which columns and relations are available to generate an SQL query relevant to the specific database.
|
| 15 |
|
| 16 |
## Spider and Spider-Syn dataset
|
| 17 |
|