Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip

<p>This study explores the use of pre-trained language models (PLMs) in tracking priming treatment induced language recovery in aphasia. We evaluate PLM-derived surprisals, the negative log-probabilities of a word or a sequence of words calculated by a PLM given its preceding context, as a con...

Full description

Saved in:
Bibliographic Details
Main Author: Yan Cong (1491478) (author)
Other Authors: Jiyeon Lee (77903) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852015373762691072
author Yan Cong (1491478)
author2 Jiyeon Lee (77903)
author2_role author
author_facet Yan Cong (1491478)
Jiyeon Lee (77903)
author_role author
dc.creator.none.fl_str_mv Yan Cong (1491478)
Jiyeon Lee (77903)
dc.date.none.fl_str_mv 2025-10-30T06:21:47Z
dc.identifier.none.fl_str_mv 10.3389/frai.2025.1668399.s001
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Data_Sheet_1_Tracking_priming-induced_language_recovery_in_aphasia_with_pre-trained_language_models_zip/30486713
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Knowledge Representation and Machine Learning
GenAI
large language models
language rehabilitation
aphasia recovery
structural priming as treatment
prompt engineering
aphasia
automatic clinical assessment
dc.title.none.fl_str_mv Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <p>This study explores the use of pre-trained language models (PLMs) in tracking priming treatment induced language recovery in aphasia. We evaluate PLM-derived surprisals, the negative log-probabilities of a word or a sequence of words calculated by a PLM given its preceding context, as a continuous and interpretable measure of treatment-induced language change. We found that surprisal scores decreased following structural priming treatment, especially in participants with more severe sentence production impairments. We also introduce a prompting-based pipeline for clinical classification tasks. It achieved promising results in classifying aphasia sentence correctness (F1 = 0.967) and detecting error categories in aphasia (accuracy = 0.846). Such use of PLMs for modeling, tracking, and automatically classifying language recovery in aphasia represents a promising deployment of GenAI in a clinical rehabilitation setting. Together, our PLM-based analyses offer a practical approach for modeling language rehabilitation, tracking not only language structure but also individual change over time in clinical contexts.</p>Clinical trial registration<p>Identifier NTC05415501.</p>
eu_rights_str_mv openAccess
id Manara_ea7c19a13485248f8a20344d01c33bdb
identifier_str_mv 10.3389/frai.2025.1668399.s001
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30486713
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zipYan Cong (1491478)Jiyeon Lee (77903)Knowledge Representation and Machine LearningGenAIlarge language modelslanguage rehabilitationaphasia recoverystructural priming as treatmentprompt engineeringaphasiaautomatic clinical assessment<p>This study explores the use of pre-trained language models (PLMs) in tracking priming treatment induced language recovery in aphasia. We evaluate PLM-derived surprisals, the negative log-probabilities of a word or a sequence of words calculated by a PLM given its preceding context, as a continuous and interpretable measure of treatment-induced language change. We found that surprisal scores decreased following structural priming treatment, especially in participants with more severe sentence production impairments. We also introduce a prompting-based pipeline for clinical classification tasks. It achieved promising results in classifying aphasia sentence correctness (F1 = 0.967) and detecting error categories in aphasia (accuracy = 0.846). Such use of PLMs for modeling, tracking, and automatically classifying language recovery in aphasia represents a promising deployment of GenAI in a clinical rehabilitation setting. Together, our PLM-based analyses offer a practical approach for modeling language rehabilitation, tracking not only language structure but also individual change over time in clinical contexts.</p>Clinical trial registration<p>Identifier NTC05415501.</p>2025-10-30T06:21:47ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.3389/frai.2025.1668399.s001https://figshare.com/articles/dataset/Data_Sheet_1_Tracking_priming-induced_language_recovery_in_aphasia_with_pre-trained_language_models_zip/30486713CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/304867132025-10-30T06:21:47Z
spellingShingle Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
Yan Cong (1491478)
Knowledge Representation and Machine Learning
GenAI
large language models
language rehabilitation
aphasia recovery
structural priming as treatment
prompt engineering
aphasia
automatic clinical assessment
status_str publishedVersion
title Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
title_full Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
title_fullStr Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
title_full_unstemmed Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
title_short Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
title_sort Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip
topic Knowledge Representation and Machine Learning
GenAI
large language models
language rehabilitation
aphasia recovery
structural priming as treatment
prompt engineering
aphasia
automatic clinical assessment