butterfliesss/MVN

Python

MVN

This repository is the implementation for our paper A multi-view network for real-time emotion recognition in conversations.

Model Architecture

Setup

Check the packages needed or simply run the command:

pip install -r requirements.txt

Download the IEMOCAP and MELD datasets from AGHMN storage.
For each dataset, we use Preprocess.py to preprocess it. You can downloaded the preprocessed datasets from here, and put them into Data/.
Download the Pretrained Word2Vec Embeddings and save it in Data/ too.

Run MVN

Run the model on IEMOCAP dataset:

bash exec_iemocap.sh

Run the model on MELD dataset:

bash exec_meld.sh

Acknowledgements

Special thanks to the AGHMN for sharing the codes and datasets.

Citation

If you find our work useful for your research, please kindly cite our paper. Thanks!

@article{ma2022multi,
  title={A multi-view network for real-time emotion recognition in conversations},
  author={Ma, Hui and Wang, Jian and Lin, Hongfei and Pan, Xuejun and Zhang, Yijia and Yang, Zhihao},
  journal={Knowledge-Based Systems},
  volume={236},
  pages={107751},
  year={2022},
  publisher={Elsevier}
}