Update README.md

README.md

@@ -20,7 +20,9 @@ inference: false
 ---
 # Background
 
-This learned metric is for evaluating models trained on the TaTA dataset. It was trained as per instructions in [TaTA: A Multilingual Table-to-Text Dataset for African Languages](https://aclanthology.org/2023.findings-emnlp.118/) (StATA-QE variant).
+This learned regression metric is for evaluating models trained on the TaTA dataset. It was trained as per instructions in [TaTA: A Multilingual Table-to-Text Dataset for African Languages](https://aclanthology.org/2023.findings-emnlp.118/) (StATA-QE variant).
+
+StATA takes as input a linearized table and an output verbalisation seperated by an " \[output\] " tag, and produces a score between 0 and 1. A score closer to 1 means the output is more understandable and atributable to the source table, values close to 0 are less so.
 
 The original file can be found [here](https://github.com/google-research/url-nlp/tree/main/tata).