Update README.md

README.md

@@ -6,6 +6,15 @@ datasets:
 
 This model employs **fine-tuning** using **Low-Rank Adaptation (LoRA)** for mapping questions to tagged questions.
 
+The tagged questions in the QueryBridge dataset are designed to train language models to understand the components and structure of a question effectively. By annotating questions with specific tags such as `<qt>`, `<p>`, `<o>`, and `<s>`, we provide a detailed breakdown of each question's elements, which aids the model in grasping the roles of different components.
+
+For example, the video below demonstrates how a model can be trained to interpret these tagged questions. We convert these annotated questions into a graph representation, which visually maps out the relationships and roles within the question. This graph-based representation facilitates the construction of queries in various query languages such as SPARQL, SQL, Cypher, and others, by translating the structured understanding into executable query formats. This approach not only enhances the model’s ability to parse and generate queries across different languages but also ensures consistency and accuracy in query formulation.
+
+
+<a href="https://youtu.be/J_N-6m8fHz0">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/664adb4a691370727c200af0/sDfp7DiYrGKvH58KdXOIY.png" alt="Training Model with Tagged Questions" width="400" height="300" />
+</a>
+
 ## Fine-Tuning with LoRA
 - Fine-tuning adjusts the model's parameters for specific tasks, enhancing its ability to handle nuanced requirements.
 - **LoRA** allows efficient updates by modifying only a subset of model weights, significantly reducing computational overhead while maintaining or improving performance.