https://github.com/philips-labs/interspeech2022-motivational-interviewing
Code for our INTERSPEECH 2022 paper submission titled "Towards Automated Counselling Decision-Making: Remarks on Therapist Action Forecasting on the AnnoMI Dataset"
https://github.com/philips-labs/interspeech2022-motivational-interviewing
Last synced: 6 months ago
JSON representation
Code for our INTERSPEECH 2022 paper submission titled "Towards Automated Counselling Decision-Making: Remarks on Therapist Action Forecasting on the AnnoMI Dataset"
- Host: GitHub
- URL: https://github.com/philips-labs/interspeech2022-motivational-interviewing
- Owner: philips-labs
- License: mit
- Created: 2022-03-29T10:52:05.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2022-10-03T08:28:09.000Z (about 3 years ago)
- Last Synced: 2025-04-30T06:07:45.740Z (6 months ago)
- Language: Jupyter Notebook
- Size: 247 KB
- Stars: 5
- Watchers: 3
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE.md
Awesome Lists containing this project
README
# Towards Automated Counselling Decision-Making: Remarks on Therapist Action Forecasting on the AnnoMI Dataset (INTERSPEECH 2022)
## Introduction
* Code for our [INTERSPEECH 2022 paper](https://www.isca-speech.org/archive/pdfs/interspeech_2022/wu22c_interspeech.pdf) titled "Towards Automated Counselling Decision-Making: Remarks on Therapist Action Forecasting on the AnnoMI Dataset"
## Environment Setup
* Note that $REPO is the folder of the repository (i.e. the folder where you see this README), after `git clone`.
```sh
cd $REPO
# install Conda environment
conda env create -f ./environment.yml
conda activate interspeechmi
# install the module
pushd $REPO/interspeechmi
python3 -m build
pip install -e .
popd
```
## Steps for reproducing our paper's results
1. `bash $REPO/interspeechmi/sh_scripts/run_and_collect_results.sh` (may take days to complete depending on your hardware)
2. Use Jupyter Notebook to run `$REPO/interspeechmi/py_scripts/plot_code_forecast_scores.ipynb`, and you'll be able to see the figures that summarise the performances under different settings.
## Dataset used
* [AnnoMI](https://github.com/uccollab/AnnoMI/archive/refs/heads/main.zip) (Wu et al. 2021)
## Citation
```bash
@inproceedings{wu22c_interspeech,
author={Zixiu Wu and Rim Helaoui and Diego {Reforgiato Recupero} and Daniele Riboni},
title={{Towards Automated Counselling Decision-Making: Remarks on Therapist Action Forecasting on the AnnoMI Dataset}},
year=2022,
booktitle={Proc. Interspeech 2022},
pages={1906--1910},
doi={10.21437/Interspeech.2022-506}
}
```