Update README.md

README.md

@@ -49,18 +49,9 @@ Below is a high-level summary of our approach:
 
 ## ⚙️ Methodology Breakdown
 
-### 1. Relevant Translation Pair Selection
-Retrieve similar translation pairs from the training set using **BM25**.  
-Code: [`BM25.py`](BM25.py)
+For full implementation details and code for all stages and baselines, please refer to our GitHub repository:
 
-### 2. Selection, Translation, and Estimation
-Perform selection, translation, and QE-guided scoring using **ICLviaQE.py**.  
-Code: [`ICLviaQE.py`](ICLviaQE.py)
-
-> 🧠 The QE model used in this step is hosted on the Hugging Face Hub:  
-> [**ICLviaQE Model**](https://huggingface.co/joyebright/ICLviaQE/tree/main)
-
-To prioritize source-target pairs with unigram overlaps, set `unigram_weight = 1` in `ICLviaQE.py` (default is `0`).
+👉 **[ICLviaQE on GitHub](https://github.com/JoyeBright/ICLviaQE)**
 
 ---