Learning from Impairment: Leveraging Insights from Clinical Linguistics in Language Modelling Research

TL;DR

This paper explores how clinical linguistics and aphasiology insights can inform the development and evaluation of more human-like, syntactically capable language models, aiming to improve their learning strategies and assessment frameworks.

Contribution

It introduces a novel perspective by integrating clinical linguistics insights into language model training and evaluation, emphasizing syntactic skills and human-inspired learning strategies.

Findings

Insights from aphasia treatment can inform LM assessment methods.

Linguistically motivated training approaches enhance syntactic understanding.

Implications for developing cognitively plausible NLP models.

Abstract

This position paper investigates the potential of integrating insights from language impairment research and its clinical treatment to develop human-inspired learning strategies and evaluation frameworks for language models (LMs). We inspect the theoretical underpinnings underlying some influential linguistically motivated training approaches derived from neurolinguistics and, particularly, aphasiology, aimed at enhancing the recovery and generalization of linguistic skills in aphasia treatment, with a primary focus on those targeting the syntactic domain. We highlight how these insights can inform the design of rigorous assessments for LMs, specifically in their handling of complex syntactic phenomena, as well as their implications for developing human-like learning strategies, aligning with efforts to create more sustainable and cognitively plausible natural language processing (NLP) models.