Update README.md

README.md

@@ -1,6 +1,16 @@
 ---
 license: mit
 ---
+
+# Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages
+
+## Model description
+This model is a fine-tuned version of the pre-trained model James-WYang/BigTranslate, specifically adjusted to handle the slot translation task. The fine-tuning process and the specific model adjustments are based on methodologies described in our recent publication https://arxiv.org/pdf/2404.02588.pdf. This model is designed to translate sentences while maintaining the integrity of annotated NLU (Natural Language Understanding) slots, which are marked with simple HTML-like tags.
+
+The input to the model should be a sentence where all NLU slots are annotated with HTML-like tags consisting of consecutive alphabetical letters (e.g., \<a\>, \<b\>, \<c\>). The model outputs the translated sentence preserving these annotations.
+
+Example: "Set the temperature on my \<a\>thermostat\<a\> to \<b\>29 degrees\<b\>."
+
 ## How to use
 
 ```python