Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation

Jongho Kim, Romain Storaï, Seung-won Hwang


Abstract
In this study, we investigate the potential of language models (LMs) in aiding patients experiencing anomia, a difficulty identifying the names of items. Identifying the intended target item from patient’s circumlocution involves the two challenges of term failure and error. (1) The terms relevant to identifying the item remain unseen. (2) What makes the challenge unique is inherent perturbed terms by semantic paraphasia, which are not exactly related to the target item, hindering the identification process. To address each, we propose robustifying the model from semantically paraphasic errors and enhancing the model with unseen terms with gradient-based selective augmentation (GradSelect). Specifically, the gradient value controls augmented data quality amid semantic errors, while the gradient variance guides the inclusion of unseen but relevant terms. Due to limited domain-specific datasets, we evaluate the model on the Tip of the Tongue dataset as an intermediary task and then apply our findings to real patient data from AphasiaBank. Our results demonstrate strong performance against baselines, aiding anomia patients by addressing the outlined challenges.
Anthology ID:
2024.findings-emnlp.616
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10513–10527
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.616
DOI:
Bibkey:
Cite (ACL):
Jongho Kim, Romain Storaï, and Seung-won Hwang. 2024. Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10513–10527, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation (Kim et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.616.pdf