| --- |
| language: |
| - vi |
| pipeline_tag: text-classification |
| tags: |
| - clickbait |
| - vietnamese |
| - phobert |
| - text-classification |
| license: mit |
| --- |
| |
| # Vietnamese Clickbait Detection |
|
|
| Mô hình phát hiện tiêu đề clickbait tiếng Việt. |
|
|
| ## Architecture |
|
|
| - Encoder: PhoBERT-base |
| - Additional layers: CNN and pooling |
| - Task: Binary classification |
| - Labels: |
| - 0: Non-clickbait |
| - 1: Clickbait |
|
|
| ## Inputs |
|
|
| The model receives: |
|
|
| - News title |
| - Lead paragraph or article context |
|
|
| ## Limitations |
|
|
| The model was trained on Vietnamese news data and may not perform reliably on: |
|
|
| - Other languages |
| - Very short or incomplete inputs |
| - Domains that differ significantly from the training dataset |
|
|
| ## Intended use |
|
|
| This repository stores the trained checkpoint used by the Streamlit demonstration application. |
