Add paper to model card.

README.md

@@ -14,6 +14,8 @@ Binary text classification model based on [`classla/bcms-bertic`](https://huggin
 
 This classifier classifies text into only two categories: Negative vs. Other. For the ternary classifier (Negative, Neutral, Positive) check [this model](https://huggingface.co/classla/bcms-bertic-parlasent-bcs-ter).
 
+For details on the dataset and the finetuning procedure, please see [this paper](https://arxiv.org/abs/2206.00929).
+
 
 ## Fine-tuning hyperparameters
 
@@ -70,3 +72,26 @@ If you use the model, please cite the following paper on which the original mode
 }
 ```
 
+and the paper describing the dataset and methods for the current finetuning:
+
+```
+@misc{https://doi.org/10.48550/arxiv.2206.00929,
+  doi = {10.48550/ARXIV.2206.00929},
+  
+  url = {https://arxiv.org/abs/2206.00929},
+  
+  author = {Mochtak, Michal and Rupnik, Peter and Ljubešič, Nikola},
+  
+  keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+  
+  title = {The ParlaSent-BCS dataset of sentiment-annotated parliamentary debates from Bosnia-Herzegovina, Croatia, and Serbia},
+  
+  publisher = {arXiv},
+  
+  year = {2022},
+  
+  copyright = {Creative Commons Attribution Share Alike 4.0 International}
+}
+```
+
+