Update README.md
Browse files
README.md
CHANGED
@@ -26,13 +26,6 @@ hf_hub_url: SemViQA/tc-infoxlm-isedsc01
|
|
26 |
|
27 |
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).
|
28 |
|
29 |
-
### **Model Achievements**
|
30 |
-
- **1st place** in the **UIT Data Science Challenge** 🏅
|
31 |
-
- **State-of-the-art** performance on:
|
32 |
-
- **ISE-DSC01** → **78.97% strict accuracy**
|
33 |
-
- **ViWikiFC** → **80.82% strict accuracy**
|
34 |
-
- **SemViQA Faster**: **7x speed improvement** over the standard model 🚀
|
35 |
-
|
36 |
## Usage Example
|
37 |
|
38 |
Direct Model Usage
|
|
|
26 |
|
27 |
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).
|
28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
## Usage Example
|
30 |
|
31 |
Direct Model Usage
|