# casualdetection

**Repository Path**: oscarlin/casualdetection

## Basic Information

- **Project Name**: casualdetection
- **Description**: No description available
- **Primary Language**: Python
- **License**: MulanPSL-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-04-05
- **Last Updated**: 2021-04-08

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Chinese causal relation detection
## Model design
we mainly design a new decoder model using the idea of object detection (like faster-rcnn). the decoder consisits of three stages: 
* predicting(or segmenting) region of interest in whole sentence(like predicting ROI)
* predicting two individual regions representing reason and result in every region predicted in the first stage. 
* predicting the relationship