Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity

TL;DR

This paper proposes a general-purpose model of perceived pragmatic similarity to improve diagnosis and treatment of communication disorders, addressing diversity, pragmatic deficits, and limited data challenges.

Contribution

It introduces a simple, effective model of pragmatic similarity that supports clinical use cases and captures relevant utterance aspects for autism and language impairments.

Findings

Simple model captures diagnostic-relevant utterance features

Supports clinical decision-making in communication disorders

Addresses data scarcity and condition diversity

Abstract

The diagnosis and treatment of individuals with communication disorders offers many opportunities for the application of speech technology, but research so far has not adequately considered: the diversity of conditions, the role of pragmatic deficits, and the challenges of limited data. This paper explores how a general-purpose model of perceived pragmatic similarity may overcome these limitations. It explains how it might support several use cases for clinicians and clients, and presents evidence that a simple model can provide value, and in particular can capture utterance aspects that are relevant to diagnoses of autism and specific language impairment.