Assistive Completion of Agrammatic Aphasic Sentences: A Transfer Learning Approach using Neurolinguistics-based Synthetic Dataset

TL;DR

This paper introduces a transfer learning approach using neurolinguistics-based synthetic datasets to improve assistive sentence completion for agrammatic aphasia patients, demonstrating promising results with a fine-tuned T5 model.

Contribution

It presents a method to generate large synthetic aphasic datasets from small studies and fine-tunes a transformer model for assistive sentence correction.

Findings

Synthetic datasets match linguistic features of aphasic speech

Fine-tuned T5 model achieves high BLEU and semantic similarity scores

Synthetic data can effectively support assistive technology development

Abstract

Damage to the inferior frontal gyrus (Broca's area) can cause agrammatic aphasia wherein patients, although able to comprehend, lack the ability to form complete sentences. This inability leads to communication gaps which cause difficulties in their daily lives. The usage of assistive devices can help in mitigating these issues and enable the patients to communicate effectively. However, due to lack of large scale studies of linguistic deficits in aphasia, research on such assistive technology is relatively limited. In this work, we present two contributions that aim to re-initiate research and development in this field. Firstly, we propose a model that uses linguistic features from small scale studies on aphasia patients and generates large scale datasets of synthetic aphasic utterances from grammatically correct datasets. We show that the mean length of utterance, the noun/verb ratio, and the simple/complex sentence ratio of our synthetic datasets correspond to the reported features of aphasic speech. Further, we demonstrate how the synthetic datasets may be utilized to develop assistive devices for aphasia patients. The pre-trained T5 transformer is fine-tuned using the generated dataset to suggest 5 corrected sentences given an aphasic utterance as input. We evaluate the efficacy of the T5 model using the BLEU and cosine semantic similarity scores. Affirming results with BLEU score of 0.827/1.00 and semantic similarity of 0.904/1.00 were obtained. These results provide a strong foundation for the concept that a synthetic dataset based on small scale studies on aphasia can be used to develop effective assistive technology.