Update README.md
Browse files
README.md
CHANGED
|
@@ -26,6 +26,8 @@ StATA takes as input a linearized table and an output verbalisation seperated by
|
|
| 26 |
|
| 27 |
The original file can be found [here](https://github.com/google-research/url-nlp/tree/main/tata).
|
| 28 |
|
|
|
|
|
|
|
| 29 |
# Performance
|
| 30 |
|
| 31 |
It achieves an RMSE loss of 0.41 on the dev split, and a Pearson correlation of 0.23 with human evaluations on the test split ("attributable" column of [this dataset](https://huggingface.co/datasets/adenhaus/stata)).
|
|
|
|
| 26 |
|
| 27 |
The original file can be found [here](https://github.com/google-research/url-nlp/tree/main/tata).
|
| 28 |
|
| 29 |
+
Paper: https://www.arxiv.org/abs/2503.23204
|
| 30 |
+
|
| 31 |
# Performance
|
| 32 |
|
| 33 |
It achieves an RMSE loss of 0.41 on the dev split, and a Pearson correlation of 0.23 with human evaluations on the test split ("attributable" column of [this dataset](https://huggingface.co/datasets/adenhaus/stata)).
|