Update README.md

README.md

@@ -16,6 +16,8 @@ pipeline_tag: text-classification
 model-index:
 - name: mdeberta-v3-base-subjectivity-bulgarian
   results: []
+datasets:
+- MatteoFasulo/clef2025_checkthat_task1_subjectivity
 ---
 
 # mdeberta-v3-base-subjectivity-bulgarian
@@ -94,51 +96,37 @@ The following hyperparameters were used during training:
 You can use this model directly with the Hugging Face `transformers` library for text classification:
 
 ```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import torch
-
-# Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("MatteoFasulo/mdeberta-v3-base-subjectivity-bulgarian")
-model = AutoModelForSequenceClassification.from_pretrained("MatteoFasulo/mdeberta-v3-base-subjectivity-bulgarian")
-
-# Example for an objective sentence (Bulgarian)
-text_objective = "Правителството обяви нови мерки за борба с инфлацията." # "The government announced new measures to combat inflation."
-inputs_objective = tokenizer(text_objective, return_tensors="pt")
-
-with torch.no_grad():
-    logits_objective = model(**inputs_objective).logits
-
-predicted_class_id_objective = logits_objective.argmax().item()
-predicted_label_objective = model.config.id2label[predicted_class_id_objective]
-
-print(f"Text: '{text_objective}'")
-print(f"Predicted label: {predicted_label_objective}")
-# Expected output: Predicted label: OBJ (or similar with score)
-
-# Example for a subjective sentence (Bulgarian)
-text_subjective = "Според мен това е най-доброто решение." # "In my opinion, this is the best decision."
-inputs_subjective = tokenizer(text_subjective, return_tensors="pt")
-with torch.no_grad():
-    logits_subjective = model(**inputs_subjective).logits
-predicted_class_id_subjective = logits_subjective.argmax().item()
-predicted_label_subjective = model.config.id2label[predicted_class_id_subjective]
-print(f"Text: '{text_subjective}'")
-print(f"Predicted label: {predicted_label_subjective}")
-# Expected output: Predicted label: SUBJ (or similar with score)
+from transformers import pipeline
+
+# Load the text classification pipeline
+classifier = pipeline(
+    "text-classification",
+    model="MatteoFasulo/mdeberta-v3-base-subjectivity-bulgarian",
+    tokenizer="microsoft/mdeberta-v3-base",
+)
+
+# Example usage:
+result1 = classifier("По принцип никой не иска войни, но за нещастие те се случват.")
+print(f"Classification: {result1}")
+# Expected output: [{'label': 'SUBJ', 'score': ...}]
+
+result2 = classifier("В един момент започнал сам да търси изход за своето спасение и здраве")
+print(f"Classification: {result2}")
+# Expected output: [{'label': 'OBJ', 'score': ...}]
 ```
 
 ## Citation
 
-If you find this work helpful or inspiring, please consider citing the original paper:
+If you find our work helpful or inspiring, please feel free to cite it:
 
 ```bibtex
-@misc{antoun2024camembert20smarterfrench,
-      title={AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles},
-      author={Matteo Fasulo and Stefan Petkov and Antonio Toral},
+@misc{fasulo2025aiwizardscheckthat2025,
+      title={AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles}, 
+      author={Matteo Fasulo and Luca Babboni and Luca Tedeschini},
       year={2025},
       eprint={2507.11764},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2507.11764},
+      url={https://arxiv.org/abs/2507.11764}, 
 }
 ```