BladeDancer957 / TSAM

The code for COLING2022 paper: 《TSAM: A Two-Stream Attention Model for Causal Emotion Entailment》

TSAM

The code for paper: 《TSAM: A Two-Stream Attention Model for Causal Emotion Entailment》

Requirements

• Python 3.6
• PyTorch 1.6
• Transformers from Hugging Face

With Anaconda, we can create the environment with the provided environment.yml:

conda env create --file environment.yml 
conda activate CEE

The code has been tested on Ubuntu 16.04 using a single GPU. For multi-GPU training, a little extra work may be needed, and please refer to these examples: Hugging Face and CLUEbenchmark.

Run Steps

1. data/ including original annotation dataset and our preprocessed dataset.
2. code/ including our codes.
3. Download necessary pre-trained model files (RoBERTa base and large).
4. Configure hyper-parameters in code/config.py
5. Run our model:

python code/main.py