Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -45,31 +45,30 @@ interface = gr.Interface(
|
|
| 45 |
fn=classify,
|
| 46 |
inputs=gr.Textbox(
|
| 47 |
lines=4,
|
| 48 |
-
placeholder="Enter text in English or Chinese...
|
| 49 |
-
label="📝 Input Text
|
| 50 |
),
|
| 51 |
-
outputs=gr.Markdown(label="📊 Prediction
|
| 52 |
-
title="🔍 Manipulative Language Detector
|
| 53 |
description="""
|
| 54 |
-
🧪
|
| 55 |
-
Enter a sentence in English or Chinese to detect if it's manipulative.
|
| 56 |
|
| 57 |
-
📌 **Disclaimer
|
| 58 |
This system is for **research and educational purposes only**.
|
| 59 |
It **does not guarantee accuracy** and **should not be used as legal or clinical evidence**.
|
| 60 |
-
本工具仅用于**学术研究与教学演示**,不构成法律、医疗或其他正式用途的依据。
|
| 61 |
|
| 62 |
-
🤖 **Model Info
|
| 63 |
- Model: `LilithHu/mbert-manipulative-detector`
|
| 64 |
- Base: `mDeBERTa-v3` multilingual pre-trained model
|
| 65 |
- Fine-tuned using HuggingFace Transformers on 10,000 labeled Chinese data
|
| 66 |
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
⚠️ **About Examples / 关于例子**
|
| 70 |
The examples provided below are those **cited in the paper**, including implicit moral coercion, polite masking and false positives.
|
| 71 |
|
| 72 |
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
""",
|
| 75 |
examples=[
|
|
|
|
| 45 |
fn=classify,
|
| 46 |
inputs=gr.Textbox(
|
| 47 |
lines=4,
|
| 48 |
+
placeholder="Enter text in English or Chinese... ",
|
| 49 |
+
label="📝 Input Text"
|
| 50 |
),
|
| 51 |
+
outputs=gr.Markdown(label="📊 Prediction"),
|
| 52 |
+
title="🔍 Manipulative Language Detector",
|
| 53 |
description="""
|
| 54 |
+
🧪 Enter a sentence in English or Chinese to detect if it's manipulative.
|
|
|
|
| 55 |
|
| 56 |
+
📌 **Disclaimer**
|
| 57 |
This system is for **research and educational purposes only**.
|
| 58 |
It **does not guarantee accuracy** and **should not be used as legal or clinical evidence**.
|
|
|
|
| 59 |
|
| 60 |
+
🤖 **Model Info**
|
| 61 |
- Model: `LilithHu/mbert-manipulative-detector`
|
| 62 |
- Base: `mDeBERTa-v3` multilingual pre-trained model
|
| 63 |
- Fine-tuned using HuggingFace Transformers on 10,000 labeled Chinese data
|
| 64 |
|
| 65 |
+
⚠️ **About Examples**
|
|
|
|
|
|
|
| 66 |
The examples provided below are those **cited in the paper**, including implicit moral coercion, polite masking and false positives.
|
| 67 |
|
| 68 |
|
| 69 |
+
🌐 **Built with Gradio and hosted on HuggingFace Spaces**
|
| 70 |
+
|
| 71 |
+
|
| 72 |
|
| 73 |
""",
|
| 74 |
examples=[
|