Update README.md

README.md

@@ -12,4 +12,7 @@ tags:
 
 **Spearman correlation coefficient** is set as the best metric to train the **sentence-level** task.
 
-Using the DCSQE framework, synthetic data is generated from the WMT2023 parallel corpus for pre-training, and then fine-tuned on the WMT2022 QE EN-DE training set, all implemented with the Fairseq framework.
+Using the DCSQE framework, synthetic data is generated from the WMT2023 parallel corpus for pre-training, and then fine-tuned on the WMT2022 QE EN-DE training set, all implemented with the Fairseq framework.
+
+For a detailed description of the DCSQE framework, please refer to the paper: <br/>
+ [Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation](https://huggingface.co/papers/2502.19941)