Update README.md

README.md

@@ -52,7 +52,7 @@ It classifies each token as part of a *Claim* or *Non-Claim* span, following the
 - **Batch size:** 16  
 - **Epochs:** 5  
 - **Max sequence length:** 512  
-- **Truncation strategy:** Sentence-level segmentation
+- **Truncation strategy:** Chunking with 128-token overlap (stride)
 
 ---
 
@@ -61,9 +61,9 @@ It classifies each token as part of a *Claim* or *Non-Claim* span, following the
 
 | **Model** | **Label** | **Precision (%)** | **Recall (%)** | **F1 (%)** |
 |------------|------------|-------------------|----------------|-------------|
-| **BERT-Sent (This model)** | Claim | 37.50 | 25.81 | 30.57 |
-| | Non-Claim | 63.35 | 76.42 | 69.27 |
-| | Micro Avg | 61.88 | 71.59 | 66.38 |
+| **BERT-Chunk** | Claim | 40.38 | 22.58 | 28.97 |
+| | Non-Claim | 55.96 | 68.71 | 61.68 |
+| | Micro Avg | 55.24 | 64.31 | 59.43 |
 
 ---