Add pipeline tag and link to paper

This PR adds the `pipeline_tag` to the model card, ensuring the model can be found at https://huggingface.co/models?pipeline_tag=text-classification. It also links to the paper [MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications](https://huggingface.co/papers/2506.19502).

README.md

@@ -1,7 +1,9 @@
 ---
 library_name: transformers
 license: mit
+pipeline_tag: text-classification
 ---
+
 ## Model Description
 
 We introduce ModCon-Task-Identifier, a fine-tuned BERT model that is capable of identifying the modality conversion task type based on the user’s prompt. 
@@ -10,4 +12,6 @@ The model was developed as a part of the Multi-Agent MATE project, the goal of w
 conversion framework. Based on the user’s query, the system will convert the input file to the desired format by changing the modality 
 (for instance, a text can be converted to an image, or a video can be converted to an audio)
 
-**The official project repository and the full project code are available at https://github.com/AlgazinovAleksandr/Multi-Agent-MATE**
+**The official project repository and the full project code are available at https://github.com/AlgazinovAleksandr/Multi-Agent-MATE**
+
+This model is based on the paper [MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications](https://huggingface.co/papers/2506.19502)