Medical short text classification via Soft Prompt-tuning

In recent decades, medical short texts, such as medical conversations and online medical inquiries, have garnered significant attention and research. The advances in the medical short text have profound implications in practical applications, particularly for classifying in-patient discharge summari...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiao Xiao, Han Wang, Feng Jiang, Tingyue Qi, Wei Wang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1519280/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183890135678976
author Xiao Xiao
Han Wang
Feng Jiang
Tingyue Qi
Wei Wang
author_facet Xiao Xiao
Han Wang
Feng Jiang
Tingyue Qi
Wei Wang
author_sort Xiao Xiao
collection DOAJ
description In recent decades, medical short texts, such as medical conversations and online medical inquiries, have garnered significant attention and research. The advances in the medical short text have profound implications in practical applications, particularly for classifying in-patient discharge summaries and medical text reports, leading to improved understandability for medical professionals. However, the challenges posed by the short length, professional medical vocabulary, complex medical measures, and feature sparsity are further magnified in medical short text classification compared to general domains. This paper introduces a novel soft prompt-tuning method designed specifically for medical short text classification. Inspired by the recent success of prompt- tuning, which has been extensively explored to enhance semantic modeling in various natural language processing tasks with the appearance of GPT-3, our method incorporates an automatic template generation method to address the issues related to short length and feature sparsity. Additionally, we propose two different strategies to expand the label word space, effectively handling the challenges associated with specialized medical vocabulary and complex medical measures in medical short texts. The experimental results demonstrate the effectiveness of our method and its potential as a significant advancement in medical short text classification. By addressing issues related to short text length, feature sparsity, and specialized medical terminology, it offers a promising advancement toward more accurate and interpretable medical text classification.
format Article
id doaj-art-08769a70b0f647d1a86cebfe85071c8c
institution OA Journals
issn 2296-858X
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-08769a70b0f647d1a86cebfe85071c8c2025-08-20T02:17:13ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-04-011210.3389/fmed.2025.15192801519280Medical short text classification via Soft Prompt-tuningXiao Xiao0Han Wang1Feng Jiang2Tingyue Qi3Wei Wang4Department of Ultrasound, The Affiliated Hospital of Yangzhou University, Yangzhou University, Yangzhou, ChinaDepartment of Information Engineering, Yangzhou University, Yangzhou, ChinaDepartment of Ultrasound, The First Affiliated Hospital of Wannan Medical College, Wuhu, ChinaDepartment of Ultrasound, The Affiliated Hospital of Yangzhou University, Yangzhou University, Yangzhou, ChinaDepartment of Radiology, The Affiliated Hospital of Yangzhou University, Yangzhou University, Yangzhou, ChinaIn recent decades, medical short texts, such as medical conversations and online medical inquiries, have garnered significant attention and research. The advances in the medical short text have profound implications in practical applications, particularly for classifying in-patient discharge summaries and medical text reports, leading to improved understandability for medical professionals. However, the challenges posed by the short length, professional medical vocabulary, complex medical measures, and feature sparsity are further magnified in medical short text classification compared to general domains. This paper introduces a novel soft prompt-tuning method designed specifically for medical short text classification. Inspired by the recent success of prompt- tuning, which has been extensively explored to enhance semantic modeling in various natural language processing tasks with the appearance of GPT-3, our method incorporates an automatic template generation method to address the issues related to short length and feature sparsity. Additionally, we propose two different strategies to expand the label word space, effectively handling the challenges associated with specialized medical vocabulary and complex medical measures in medical short texts. The experimental results demonstrate the effectiveness of our method and its potential as a significant advancement in medical short text classification. By addressing issues related to short text length, feature sparsity, and specialized medical terminology, it offers a promising advancement toward more accurate and interpretable medical text classification.https://www.frontiersin.org/articles/10.3389/fmed.2025.1519280/fullmedical short textshort text classificationprompt-tuningsoft promptNLP
spellingShingle Xiao Xiao
Han Wang
Feng Jiang
Tingyue Qi
Wei Wang
Medical short text classification via Soft Prompt-tuning
Frontiers in Medicine
medical short text
short text classification
prompt-tuning
soft prompt
NLP
title Medical short text classification via Soft Prompt-tuning
title_full Medical short text classification via Soft Prompt-tuning
title_fullStr Medical short text classification via Soft Prompt-tuning
title_full_unstemmed Medical short text classification via Soft Prompt-tuning
title_short Medical short text classification via Soft Prompt-tuning
title_sort medical short text classification via soft prompt tuning
topic medical short text
short text classification
prompt-tuning
soft prompt
NLP
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1519280/full
work_keys_str_mv AT xiaoxiao medicalshorttextclassificationviasoftprompttuning
AT hanwang medicalshorttextclassificationviasoftprompttuning
AT fengjiang medicalshorttextclassificationviasoftprompttuning
AT tingyueqi medicalshorttextclassificationviasoftprompttuning
AT weiwang medicalshorttextclassificationviasoftprompttuning