Improve model card and add paper abstract

README.md

@@ -2,19 +2,20 @@
 language:
 - vi
 library_name: transformers
+license: mit
+pipeline_tag: text-classification
 tags:
 - SemViQA
 - three-class-classification
 - fact-checking
-pipeline_tag: text-classification
-license: mit
+hf_hub_url: SemViQA/tc-infoxlm-isedsc01
 ---
 
 # SemViQA-TC: Vietnamese Three-class Classification for Claim Verification  
 
 ## Model Description  
 
-**SemViQA-TC** is one of the key components of the **SemViQA** system, designed for **three-class classification** in Vietnamese fact-checking. This model classifies a given claim into one of three categories: **SUPPORTED**, **REFUTED**, or **NOT ENOUGH INFORMATION (NEI)** based on retrieved evidence.
+**SemViQA-TC** is one of the key components of the **SemViQA** system, designed for **three-class classification** in Vietnamese fact-checking. This model classifies a given claim into one of three categories: **SUPPORTED**, **REFUTED**, or **NOT ENOUGH INFORMATION (NEI)** based on retrieved evidence.  This model contributes to addressing the growing need for robust fact-checking solutions, particularly for low-resource languages like Vietnamese, where existing methods often struggle with semantic nuances and complex linguistic structures.  SemViQA aims to balance precision and speed in fact verification.
 
 ### **Model Information**  
 - **Developed by:** [SemViQA Research Team](https://huggingface.co/SemViQA)  
@@ -23,7 +24,14 @@ license: mit
 - **Task:** Three-Class Classification (Fact Verification)  
 - **Dataset:** [ISE-DSC01](https://codalab.lisn.upsaclay.fr/competitions/15497)  
 
-SemViQA-TC serves as the **first step in the two-step classification process** of the SemViQA system. It initially categorizes claims into three classes: **SUPPORTED, REFUTED, or NEI**. For claims classified as **SUPPORTED** or **REFUTED**, a secondary **binary classification model (SemViQA-BC)** further refines the prediction. This hierarchical classification strategy enhances the accuracy of fact verification.
+SemViQA-TC serves as the **first step in the two-step classification process** of the SemViQA system. It initially categorizes claims into three classes: **SUPPORTED, REFUTED, or NEI**. For claims classified as **SUPPORTED** or **REFUTED**, a secondary **binary classification model (SemViQA-BC)** further refines the prediction. This hierarchical classification strategy enhances the accuracy of fact verification.  This approach aims to achieve state-of-the-art results by combining Semantic-based Evidence Retrieval (SER) and Two-step Verdict Classification (TVC).
+
+### **Model Achievements**
+- **1st place** in the **UIT Data Science Challenge** 🏅  
+- **State-of-the-art** performance on:  
+  - **ISE-DSC01** → **78.97% strict accuracy**  
+  - **ViWikiFC** → **80.82% strict accuracy**  
+- **SemViQA Faster**: **7x speed improvement** over the standard model 🚀  
 
 ## Usage Example