Update README.md

README.md

@@ -1,3 +1,16 @@
 ---
 license: mit
 ---
+
+This is a fine-tuned BERT-based language model to classify NLP-related research papers as "survey" or "non-survey" papers. The model is fine-tuned on a dataset of 787 survey and 11,805 non-survey papers from the ACL Anthology and the arXiv cs.CL category. Prior to fine-tuning, the model is initialized with weights from Prior to fine-tuning, the model is initialized with weights from [malteos/scincl](https://huggingface.co/malteos/scincl).
+
+
+
+## Evaluation Results
+
+The model was evaluated on 20% test data.
+
+* **F1:** 84.35
+* **Precision:** 82.38
+* **Recall:** 86.53
+* **Accuracy:** 98.04