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

TL;DR

This paper introduces a gradient-based selective augmentation method to improve language models in identifying intended targets for anomia patients, addressing semantic errors and unseen terms to enhance assistive accuracy.

Contribution

The study proposes a novel gradient-guided data augmentation technique to robustify language models specifically for anomia patient assistance, a previously underexplored application.

Findings

Model outperforms baselines on Tip-of-the-Tongue dataset.

Effective handling of semantic paraphasic errors.

Improved target identification on real patient data.

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. 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.