Version 1
: Received: 10 June 2024 / Approved: 10 June 2024 / Online: 11 June 2024 (11:39:31 CEST)
How to cite:
Soleimani, R.; Guo, S.; Haley, K.; Jacks, A.; Lobaton, E. The Impact of Pause and Filler Words Encoding on Dementia Detection with Contrastive Learning. Preprints2024, 2024060665. https://doi.org/10.20944/preprints202406.0665.v1
Soleimani, R.; Guo, S.; Haley, K.; Jacks, A.; Lobaton, E. The Impact of Pause and Filler Words Encoding on Dementia Detection with Contrastive Learning. Preprints 2024, 2024060665. https://doi.org/10.20944/preprints202406.0665.v1
Soleimani, R.; Guo, S.; Haley, K.; Jacks, A.; Lobaton, E. The Impact of Pause and Filler Words Encoding on Dementia Detection with Contrastive Learning. Preprints2024, 2024060665. https://doi.org/10.20944/preprints202406.0665.v1
APA Style
Soleimani, R., Guo, S., Haley, K., Jacks, A., & Lobaton, E. (2024). The Impact of Pause and Filler Words Encoding on Dementia Detection with Contrastive Learning. Preprints. https://doi.org/10.20944/preprints202406.0665.v1
Chicago/Turabian Style
Soleimani, R., Adam Jacks and Edgar Lobaton. 2024 "The Impact of Pause and Filler Words Encoding on Dementia Detection with Contrastive Learning" Preprints. https://doi.org/10.20944/preprints202406.0665.v1
Abstract
Dementia, primarily caused by neurodegenerative diseases like Alzheimer’s disease (AD), affects millions worldwide, making detection and monitoring crucial. To enable these tasks, we propose encoding in-text pauses and filler words (i.e., “uh” and “um”) in text-based language models, and thoroughly evaluate their effect in performance. Additionally, we suggest using contrastive learning to improve performance in a multi-task framework. Our results demonstrated the effectiveness of our approaches in enhancing the model’s performance, achieving 87% accuracy and an 86% F1-score. Compared to the state-of-the-art, our approach has similar performance despite having significantly fewer parameters. This highlights the importance of pause and filler word encoding on the detection of dementia.
Keywords
Dementia; Contrastive learning; Deep learning; Text classification, LLMs, NLP
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
