This repository contains the implementation code for the paper titled Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia.
This work utilizes the Pit and ADReSS dementia corpora. Access to the data is password-protected and restricted to individuals who have signed an agreement. For additional information, please visit the DementiaBank website.
- Standard-finetune:
python train.py --model_name RoBERTa - Multitask MLM:
python train.py --model_name RoBERTa_Multitask - Entailment:
python train.py --model_name RoBERTa_entail - Standard−prompt:
python train_prompt.py --model_name RoBERTa_Prompt - Prompt−demonstrations:
python train_prompt.py --model_name RoBERTa_Prompt_dem - Prompt−inverse:
python train_prompt.py --model_name RoBERTa_Prompt_inverse
- Standard-finetune:
python test.py --model_name RoBERTa - Multitask MLM:
python test.py --model_name RoBERTa_Multitask - Entailment:
python test.py --model_name RoBERTa_entail - Standard−prompt:
python test_prompt.py --model_name RoBERTa_Prompt - Prompt−demonstrations:
python test_prompt.py --model_name RoBERTa_Prompt_dem - Prompt−inverse:
python test_prompt.py --model_name RoBERTa_Prompt_inverse
- Fork the repository
- Create a new branch:
git checkout -b feature/your-feature - Make your changes and commit them:
git commit -m 'Add your feature - Push to the branch:
git push origin feature/your-feature - Submit a pull request
Dimitris Gkoumas. For more information, please visit gkoumasd.github.io
If you find this project useful for your research, please consider citing it using the following BibTeX entry:
@inproceedings{gkoumas2023reformulating,
title={Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia.},
author={Gkoumas, Dimitris and Purver, Matthew and Liakata, Maria},
booktitle={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
pages={15904--15917},
year={2023}
}