Automating Intended Target Identification for Paraphasias in Discourse Using a Large Language Model

Author:

Salem Alexandra C.1ORCID,Gale Robert C.1,Fleegle Mikala2,Fergadiotis Gerasimos2ORCID,Bedrick Steven1ORCID

Affiliation:

1. Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland

2. Department of Speech & Hearing Sciences, Portland State University, OR

Abstract

Purpose: To date, there are no automated tools for the identification and fine-grained classification of paraphasias within discourse, the production of which is the hallmark characteristic of most people with aphasia (PWA). In this work, we fine-tune a large language model (LLM) to automatically predict paraphasia targets in Cinderella story retellings. Method: Data consisted of 332 Cinderella story retellings containing 2,489 paraphasias from PWA, for which research assistants identified their intended targets. We supplemented these training data with 256 sessions from control participants, to which we added 2,415 synthetic paraphasias. We conducted four experiments using different training data configurations to fine-tune the LLM to automatically “fill in the blank” of the paraphasia with a predicted target, given the context of the rest of the story retelling. We tested the experiments' predictions against our human-identified targets and stratified our results by ambiguity of the targets and clinical factors. Results: The model trained on controls and PWA achieved 50.7% accuracy at exactly matching the human-identified target. Fine-tuning on PWA data, with or without controls, led to comparable performance. The model performed better on targets with less human ambiguity and on paraphasias from participants with fluent or less severe aphasia. Conclusions: We were able to automatically identify the intended target of paraphasias in discourse using just the surrounding language about half of the time. These findings take us a step closer to automatic aphasic discourse analysis. In future work, we will incorporate phonological information from the paraphasia to further improve predictive utility. Supplemental Material: https://doi.org/10.23641/asha.24463543

Publisher

American Speech Language Hearing Association

Subject

Speech and Hearing,Linguistics and Language,Language and Linguistics

Reference72 articles.

1. Target word prediction and paraphasia classification in spoken discourse;Adams J.;BioNLP,2017

2. To BERT or not to BERT: Comparing speech and language-based approaches for Alzheimer's disease detection;Balagopalan A.;Interspeech,2020

3. Reconciling modern machine-learning practice and the classical bias–variance trade-off

4. Bock, K. (1995). Sentence production: From mind to mouth. In J. L. Miller & P. D. Eimas (Eds.), Speech, language, and communication (pp. 181–216). Elsevier. https://doi.org/10.1016/B978-012497770-9/50008-X

5. The Consolidated Framework for Implementation Research (CFIR): a useful theoretical framework for guiding and evaluating a guideline implementation process in a hospital-based nursing practice

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3